FDA enforcement recalls (drugs, devices, food) — search by product keyword, or most recent when no query. Returns product, reason, classification, status, company. Source: openFDA (U.S. FDA), public data.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (1-20, default 5) | |
| product | No | Product description or keyword (e.g. 'aspirin', 'syringe', 'peanut butter') |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden for behavioral disclosure. It adds context about the source (openFDA, U.S. FDA), public data availability, the return fields (product, reason, classification, status, company), and the no-query behavior. It does not explicitly state it is read-only, but that is implicit from the domain.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, front-loaded with the core purpose, and includes no filler. It efficiently communicates the action, scope, search behavior, return fields, and data source without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with two fully described optional parameters and no output schema, the description is sufficiently complete. It covers the purpose, source, return fields, and behavior with or without a query. It could mention pagination or temporal scope, but the core context is well covered.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Both parameters (limit and product) are fully described in the input schema, including defaults, ranges, and examples. The description adds no additional parameter semantics beyond what the schema already provides, so a baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool provides FDA enforcement recalls for drugs, devices, and food, and explains how to search by product keyword or get the most recent when no query. It is specific about the resource and scope, though it does not explicitly distinguish itself from sibling tools like fda_recalls or health_recalls_by_company.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by describing behavior with and without a query, but it does not provide explicit exclusions or alternatives among the many similar health/FDA sibling tools. It gives context for when to use it but not for when to avoid it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tool groups have overlapping purposes: fda_drug_labels vs health_drug_search, fda_recalls vs health_recalls, fx_official_rates vs treasury_fx_rates, treasury_debt vs us_debt_current, and get_gdp vs get_bea_gdp. These near-duplicates create real ambiguity for an agent deciding which tool to call.
Names mix verb-led styles (get_, search_, compare_, screen_) with domain-led styles (fx_, treasury_, uk_, health_, eurostat_, datausa_). Within the same domain, similar actions use different patterns (get_gdp vs eurostat_gdp vs imf_indicator), making the set feel inconsistent and hard to predict.
75 tools is extreme for any MCP server, especially when many tools are redundant or cover unrelated domains (weather, earthquakes, scholarly search, air quality) outside the stated SEC/economics/demographics/FX focus. This overwhelms agents and burdens context windows.
Core domains like SEC financials, major economic indicators, basic demographics, and current FX rates are well covered. However, gaps remain: no historical FX rates, no stock price/quote tool, limited demographic breakdowns, and no ability to fetch full SEC filing text. Some operations end in dead ends.