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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it warns that 'No match is not proof of safety,' and notes each match has a confidence level, which is not in the annotations. It does not contradict any annotation.

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 sentences with no filler. The first sentence front-loads the action, scope, and output content; the second adds a critical caveat. Every word 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?

The description covers purpose, scope, output elements, and a caveat. It does not explicitly mention the 'since' filter or that vehicle recalls are excluded, but those are inferable from the schema and sibling tools. The presence of an output schema means return-value details need not be repeated. Overall it gives an agent enough to call it correctly for most cases.

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 75% (3 of 4 params have descriptions). The description reinforces the meaning of 'query' (product, brand, model) and 'upc' (barcode) by listing search keys. It does not add to 'since' (filter by date) or 'sources' (agency enum), but those are reasonably self-explanatory from the schema (pattern and enum). The description adds enough value for the main search parameters to exceed the baseline.

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 states a specific verb ('Searches'), a clear resource ('US recalls'), and the exact scope ('CPSC consumer products and FDA food, drugs and devices'). It also enumerates search keys (name, brand, model number, UPC) and output elements (confidence, hazard, remedy, date). This distinguishes it from sibling vehicle_recalls, which is not mentioned but clearly outside the stated agencies.

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 when to use it (for CPSC/FDA recalls) and implicitly that vehicle_recalls would be for vehicles, but it never explicitly says 'use vehicle_recalls for vehicles' or 'use recent_recalls for recent lists.' It provides clear context (US, CPSC/FDA) but lacks explicit exclusions or alternative selection criteria.

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?

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds useful behavioral context such as 'newest first' and 'up to 90' days, but does not go much beyond that. No contradiction with annotations exists.

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 entire description is one efficient, front-loaded sentence that conveys scope, source, time range, ordering, and optional filtering without any filler or redundant wording.

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 read-only listing tool with two optional parameters and an output schema present, the description provides the essential operational details: data sources, time window, filtering, and order. Minor gaps like an explicit all-agencies default are not material given the schema covers the default.

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?

With schema description coverage at only 50%, the description compensates by clarifying that 'days' is a lookback window capped at 90 and that 'agency' is an optional single-agency filter. The enum values are self-explanatory, so the added meaning is adequate for both 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 clearly names a specific resource ('newest US recalls from CPSC and FDA') and the operation scope, with a time window and optional agency filter. It does not explicitly distinguish itself from sibling tools check_recalls or vehicle_recalls, so it falls short of 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 implies when to use it: to retrieve recent recalls within a certain number of days, optionally filtered by agency. However, it provides no explicit guidance on when to prefer this tool over check_recalls or vehicle_recalls, nor any exclusion criteria.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds genuine behavioral context beyond that: VIN input is decoded with its check digit verified, and the caveat that recall campaigns apply to the model, not proof a given VIN is unrepaired, sets clear expectations about result interpretation. No contradiction with annotations.

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 sentences with no filler; the first front-loads the purpose, lookup modes, and output fields, and the second adds a single high-value caveat. 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?

Given an output schema covers return structure and annotations cover the read-only/idempotent profile, the description covers purpose, lookup modes, output contents, and a key interpretive caveat. The main gap is parameter combination semantics (all four params optional, alternative lookup modes), which an agent would need to invoke 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?

With 0% schema description coverage, the description carries the full burden of parameter meaning and largely meets it: it explains that vin is one lookup key (decoded, check-digit verified) and that make, model, and year form an alternative lookup path. It does not clarify combination rules, such as whether VIN and make/model/year are mutually exclusive or what happens if no parameters are supplied.

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 names a specific verb and resource — 'NHTSA safety recalls for a vehicle' — and enumerates the two lookup modes (VIN or make/model/year) plus the exact fields returned (campaign number, date, component, summary, consequence, remedy, park status). The closing caveat about model-level applicability clarifies what the tool does and does not prove, which helps an agent distinguish it from a repair-status checker.

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 when to use the tool — when recall information for a vehicle is needed — and warns that results are model-level, not proof a VIN is unrepaired. However, it never names the sibling tools (recent_recalls, check_recalls) or states when one should be preferred, so routing guidance is left implicit rather than explicit.

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