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

Annotations already provide readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the description only needs to add context beyond that. It successfully adds that results include 'original citations' and that the data source is limited to 'official' records, which clarifies what kind of evidence the user can expect. It also disclaims 'not confirmed factory disruptions,' a scope boundary that is not in the annotations. However, it does not disclose whether pagination, rate limiting, or result ordering are handled, but given the annotations cover safety and idempotency, this is acceptable.

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, compact sentence that places the core action and target first, then adds the citation detail and the clarifying exclusion. No filler words or redundant restatements of the title or annotations. It earns its place by adding the scope and a negative use-case hint in minimal space.

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 no output schema and five optional parameters, the description is too sparse. It does not explain what kind of incident or recall data will be returned, how results are ordered, how pagination works, or what values are expected for source/category. The 'selected NWS records' phrase is ambiguous, and no mention of typical use cases beyond 'search' is made. Even with annotations covering safety, an agent would need to experiment or rely on external knowledge to use this confidently.

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 0%, so the description carries the full burden of explaining parameters. It does not mention any of the five parameters (limit, query, region, source, category) or suggest how they interact with the search scope. The input schema's property names and types are self-evident only at a surface level; without any description of what each parameter controls, agents will struggle to craft effective queries. This is a significant gap.

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 ('Search') and a specific set of resources ('official USGS, FEMA, FDA and selected NWS records'), which clearly identifies the tool's purpose. It also distinguishes itself from related siblings by noting 'not confirmed factory disruptions,' steering agents away from unverified supply disruption content. The phrase 'with original citations' adds further concreteness about the nature of results.

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 gives no explicit guidance on when to use this tool instead of the many sibling tools covering the same agencies (e.g., fda_recall_search_basic, fema_disaster_declarations_basic, nws_active_alerts_basic). The only comparative hint is the negative clause 'not confirmed factory disruptions,' which addresses one adjacent use case but does not explain how this feed differs from the agency-specific search tools or when an agent should pick one over the other. No exclusions or prerequisites are mentioned.

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