cpsc-recalls-mcp-server

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safe-read nature is covered. The description adds valuable context beyond annotations: it specifies what the complete record includes (hazard, remedy, product variants, incident reports, images, official URL) and clarifies CPSC's jurisdiction scope. It doesn't mention rate limits or errors, but those are not expected for a simple detail fetch with good annotation coverage.

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 tight and purposeful. It opens with the core purpose, lists the return content in a clear sequence, gives a direct usage instruction with named siblings, and closes with the jurisdictional context. There is no redundant wording; every clause earns its place.

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?

This is a single-parameter tool with an output schema present. The description covers the purpose, the exact recall-number source, the full content of the response, the usage workflow (after search/recent), and the domain boundary. Nothing necessary is missing for an agent to use it correctly.

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 input schema covers the parameter recall_number with 100% detail: pattern, format examples (modern vs historical), and where to obtain it (from cpsc_search_recalls). The tool description does not add any parameter information beyond what the schema already provides, so the baseline 3 applies.

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 verb 'Get' and specific resource: full detail for a single CPSC recall by recall number. It lists the structured contents returned (hazard description, remedy, variants, etc.), and the title aligns. The sibling tools (cpsc_get_recent, cpsc_search_recalls) are distinct because they are list-oriented, while this tool is explicitly for a single recall detail.

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?

Explicitly instructs 'Use after cpsc_search_recalls or cpsc_get_recent to get the full picture on a specific recall', naming the alternative tools and the sequencing. It also sets a jurisdiction boundary: CPSC covers consumer products only, and lists excluded categories (food, vehicles, drugs, pesticides) covered by other agencies—this tells the agent when not to use this tool.

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?

Beyond the readOnlyHint annotation, the description reveals important behavioral traits: the default 30-day window, the risk of retrieving all 9,800+ records without a date filter, and the non-intuitive pagination behavior where narrowing the window drops oldest records rather than advancing past the newest. This is exactly the kind of context that helps an agent avoid surprises.

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 five sentences long but every sentence carries distinct, high-value information: purpose, use case, date-window default, pagination caveat, and jurisdiction. It is front-loaded with the most important purpose statement and includes no redundant or filler content.

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?

Combined with a full input schema and an output schema, the description covers the tool's purpose, typical use cases, date-window behavior, pagination approach, and scope of CPSC jurisdiction. An agent has enough context to select and invoke this tool correctly without needing additional information.

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 already documents all three parameters with 100% coverage, providing a solid baseline. The description adds meaningful semantic context about the interaction between days and offset (narrowing days cannot page), which is not in the schema and helps an agent understand the parameter behavior more deeply.

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 action ('Fetch the most recent CPSC consumer product recalls') and the ordering ('newest-first'). It also distinguishes this tool from the sibling search/get tools by emphasizing recency and 'what's been recalled lately?' use cases, making the purpose unambiguous.

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 explicitly says when to use the tool ('Use for "what's been recalled lately?" or a product safety feed') and provides critical operational guidance about the date window and pagination limitations. However, it does not explicitly name the sibling tools as alternatives or state when not to use it (e.g., for keyword search), so it falls just short of a 5.

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?

Even with readOnlyHint and idempotentHint annotations, the description adds substantial behavioral context: 'All filter fields are optional substring matches that combine with AND,' 'hazard_search... Matches when the term appears in any of: hazard descriptions, product names, or remedy instructions (OR across the three),' 'Page past limit with offset — total_found and has_more say where the window sits,' and a warning that the upstream Hazard parameter 'never matches.' These disclose client-side vs upstream behavior and subtle matching semantics beyond what annotations convey.

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 dense but every sentence adds value: scope, exclusions, matching behavior, per-field strategies, pagination, and handoff to a sibling tool. It is front-loaded with the core purpose and progresses logically through nuances without repetition or filler.

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 tool with 15 parameters, an output schema, and sibling tools, the description is remarkably complete. It covers domain scope, non-coverage, filter combination logic, client-side vs upstream execution, pagination semantics, and when to delegate to cpsc_get_recall. The existence of an output schema means return-value details need not be repeated, so the description is fully sufficient for an agent to invoke the tool correctly.

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 100%, but the description enriches key parameters: title_search is called the 'highest-signal single filter,' hazard_search explains its OR semantics across three fields, remedy is contrasted with the structured enum, and manufacturer/retailer/importer roles are clarified with fallback guidance. The description goes well beyond schema descriptions in helping the agent choose and combine parameters.

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 opens with an explicit verb+resource statement: 'Search consumer product recalls from the CPSC (Consumer Product Safety Commission) database.' It further clarifies scope by listing product categories and enumerating exclusions (FDA, NHTSA, USCG, EPA). It also distinguishes from the sibling tool cpsc_get_recall by directing users to that tool for full record retrieval, making the search-vs-fetch role clear.

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?

Provides explicit when-to-use guidance: 'Start with title_search when you have a product in hand,' 'For hazard-type filtering... use hazard_search,' and 'When manufacturer returns no results, try importer, retailer, or distributor.' It also tells users when NOT to use the tool via the exclusions (food/drugs, vehicles, etc.) and points to cpsc_get_recall for fetching details.

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