US FDA Recalls (Food, Drug, Device) MCP

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description does the useful work of stating the result cap ('Latest 5') and a cost signal ('FREE'), which tell the agent about output volume and pricing. However, it omits what happens when no keyword is supplied (0 required params) and gives no indication of freshness window or return fields.

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?

A single front-loaded sentence with zero waste; the cost signal and the core behavior come first, followed by the match dimensions.

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 two-param tool with no output schema, the description covers purpose and matching behavior but leaves open the default behavior when both optional parameters are omitted. With 0 required params, that no-argument case is a real gap.

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?

The schema only documents the 'type' enum; the 'keyword' parameter has no schema description. The description compensates by explaining what the keyword matches (product, firm, allergen, pathogen), which meaningfully clarifies the undocumented parameter beyond the schema.

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?

States a specific verb+resource ('Latest 5 FDA recalls') with clear scope (food/drug/device) and filterable dimensions (product, firm, allergen, pathogen). This differentiates it implicitly from recall_search because it emphasizes recency and a hard cap of 5, though it never names the sibling directly.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no alternative is named. The agent must infer from 'Latest 5' that this is a lightweight recent-recall lookup versus a full recall_search, but that inference is left entirely to the reader.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It does disclose a result cap of 100 and the data domains searched, but omits authentication requirements, pagination/truncation behavior, and the read-only nature of the operation.

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 a single short sentence that front-loads the result cap and data domains. The leading 'PRO.' is cryptic and the sentence omits important context, but it is compact with little wasted text.

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?

With six parameters, no annotations, no output schema, and low schema coverage, the description should do more. It names several filters but lacks usage guidance against siblings, authentication context, and return or pagination details, leaving the agent under-informed.

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?

Schema description coverage is only 33%, so the description must compensate. It adds meaningful filter semantics: keyword, class I/II/III, state, and since date, and implies the types array maps to food, drugs, and devices, though it does not fully document access_token or types explicitly.

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 identifies the resource as recalls across food, drugs, and devices, and indicates filtering capability. It does not explicitly distinguish this search tool from siblings like latest_recalls or watchlist, which keeps it from a 5.

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 lists available filters but gives no explicit guidance on when to use this tool versus latest_recalls or watchlist. It implies usage through the phrase 'with filters,' but provides no exclusions, prerequisites, or alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does disclose useful behavior: a PRO/paid tier requirement, a hard cap of 50 items, and a default 90-day window. It omits return shape, error behavior for oversized lists, and whether matching is exact or fuzzy — substantial gaps for a zero-annotation tool.

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?

Two short sentences, front-loaded with the tier marker and the core operation, then the constraint and default. Nothing is wasted or padded.

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?

With no annotations and no output schema, the description should say more about what a check returns (matches? recall counts? per-item status?) and what happens with invalid or excess items. It covers scope and limits well but leaves the result contract entirely unspecified.

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?

Schema coverage is only 33%, so the description must compensate, and it largely does: 'up to 50' explains the items array semantics and 'last N days (default 90)' gives both meaning and default for days. The access_token parameter is already documented in the schema; only item string format (exact names vs IDs) remains unclear.

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 gives a specific verb ('Check') and resource ('up to 50 suppliers/brands/products against recalls'), plus a time window. It is clearly a batch watchlist check rather than a single recall lookup, which implicitly distinguishes it from latest_recalls and recall_search, but it never names those siblings.

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?

Usage is only implied: a capped list of items (50) suggests 'use this when monitoring a set of entities' versus the sibling tools that browse/search recalls. There is no explicit when-to-use, when-not-to-use, or named alternative, and no note on what to do if the list exceeds 50.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.