Tools

Fourteen tools for querying FDA data across drugs, food, devices, animal/veterinary products, and recalls — plus an optional DataCanvas SQL surface for large result sets:

The nine record-returning tools bound their page at ~24 KB. openFDA record size is not something a caller can see in advance — a drug/event report averages ~34 KB against ~440 bytes for a food/event report, so limit: 10 means very different things per endpoint. The eight multi-row search tools return as many records of the requested window as fit, then report the withheld count on page_omitted alongside the byte figure and the routes to the rest (the exact skip to continue from, a lower limit, stage: true for SQL, or openfda_count_values for a distribution). Whenever anything matched, at least one record comes back, whatever it measures. openfda_get_drug_label returns a section outline instead, since its payload is one document rather than many rows.

openfda_drug_profile

Resolve one drug name to its FDA identity, then return a consolidated profile in a single call — replacing four or five chained lookups.

• Resolves a brand or generic name to canonical FDA identifiers once (generic name, NDC, RxCUI, SPL set ID), then keys every sub-query off that identity to avoid the identifier drift that breaks naive tool chaining
• Single-ingredient resolution: a single-drug query won't resolve to a combination product
• Sections: label highlights, adverse-event summary (top reactions, serious count), recall history, Drugs@FDA approval, and current shortage status
• Best-effort — a miss on any section returns null rather than failing the whole call; use the dedicated tool for a deep dive into any area

openfda_search_adverse_events

Search adverse event reports across drugs, food, and devices. Use to investigate safety signals, find reports for a specific product, or explore reactions by demographics.

• Category selection: drug, food, or device — each returns different field schemas
• Elasticsearch query syntax for filtering by product, reaction, seriousness, date range
• Pagination via limit (up to 1000) and skip (openFDA's ceiling is 25000 — past it the call returns a typed pagination_limit_reached error with recovery guidance)
• drug/event is the largest-record endpoint openFDA serves, so this is where the ~24 KB page budget bites hardest: a default limit: 10 on drug reports typically returns one to three of them with the rest disclosed on page_omitted, where the same call on food reports returns all ten
• Formatted output includes report ID, seriousness, patient demographics, reactions, drugs with characterization/indication/route, and all remaining fields

openfda_count_values

Aggregate and tally unique values for any field across any openFDA endpoint. Returns ranked term-count pairs sorted by count descending.

• Works across all 20 openFDA endpoints (drugs, food, devices, animal/veterinary, tobacco, other)
• Use .exact suffix on field names for whole-phrase counting
• Optional search filter to scope the aggregation
• Returns up to 1000 terms per query

openfda_search_recalls

Search enforcement reports and recall actions across drugs, food, and devices.

• Supports enforcement (all categories) and recall (devices only) endpoints
• Filter by classification (Class I/II/III), recalling firm, reason, status
• Formatted output includes recall number, classification, product description, reason, distribution pattern

openfda_search_device_clearances

Search FDA device premarket notifications — 510(k) clearances and PMA approvals.

• Two pathways: 510k (174K+ records, most common) and pma (higher-risk devices)
• Filter by applicant, product code, advisory committee, device name
• Formatted output adapts to pathway: 510(k) shows K-number/clearance type, PMA shows supplement info

openfda_get_drug_label

Look up FDA drug labeling (package inserts / SPL documents). Check indications, warnings, dosage, contraindications, active ingredients, or any structured label section.

• Search by brand name, generic name, manufacturer, or set ID
• Formatted output dynamically renders all label sections and openfda metadata present in the record, in full — content[] and structuredContent carry the same text
• A page over the ~24 KB inline budget returns kind: "outline" — the section names and their sizes — instead of the label text; re-call with sections: [...] for the ones you need
• Outline sizes are summed across the page, so a section's cost scales with limit — the re-call guidance names a section measured to fit the budget at the requested limit and quotes its byte size
• sections narrows each record to the requested keys plus metadata (openfda, set_id, id, effective_time, version); a selection over the budget is returned whole, never trimmed, with its serialized size reported
• Default limit of 5 — labels are large documents (a warfarin label is ~130 KB on its own)

openfda_search_drug_approvals

Search the Drugs@FDA database for drug application approvals (NDAs and ANDAs). Returns application details, sponsor info, and full submission history.

• Filter by brand name, sponsor, submission type, review priority
• Formatted output includes products with active ingredients, dosage forms, routes, and marketing status
• Full submission history with type, status, date, and review priority
• Pagination via limit (up to 1000) and skip (openFDA's ceiling is 25000 — past it the call returns a typed pagination_limit_reached error with recovery guidance)

openfda_lookup_ndc

Look up drugs in the NDC (National Drug Code) Directory. Identify drug products by NDC code, find active ingredients, packaging details, or manufacturer info.

• Search by product NDC, brand name, generic name, manufacturer, or active ingredient
• Returns product details, active ingredients with strengths, and packaging information
• Sortable by listing expiration date or other fields

openfda_search_animal_events

Search adverse event reports for veterinary drugs and devices submitted to the FDA Center for Veterinary Medicine (1.3M+ records).