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

Annotations already mark it read-only, idempotent, and non-destructive, and the description adds meaningful behavior beyond that: a 200-bridge per-call cap, sorting by lowest sufficiency rating, data vintage (FHWA NBI as of June 2023, updated annually), broad coverage, and no-auth public domain access. This goes well beyond what the annotations alone provide.

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 front-loaded with the core action and then adds useful context about results, coverage, data recency, and auth. The long enumeration of returned fields is slightly redundant given an output schema exists, but every sentence still contributes selection-relevant information.

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 read-only search tool, the description covers what is searched, how results are filtered and sorted, the result limit, the returned attributes, dataset scope and vintage, and authentication requirements. With the output schema and annotations present, an agent has everything needed to decide whether to call it and how to invoke 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 has 100% description coverage, including the FIPS state_code format, the G/F/P condition enum, and the limit range/default, so the baseline is 3. The description reinforces 'Good / Fair / Poor' and the optional condition filter, but it does not add material parameter meaning 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?

The description opens with a specific verb and resource: 'Search the National Bridge Inventory (NBI) for highway bridges in a US state,' and immediately adds the optional condition filter. It is clearly a list/search operation rather than a detail, stats, or nearby lookup, so it stands apart from the sibling nbi.infrastructure tools.

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 clear context for when to call it: searching bridges by US state with an optional condition filter, with a result cap and sort order. It does not explicitly name alternatives or say when not to use it, such as pointing to bridge_detail for a single bridge or nearby for proximity searches, so it misses the explicit exclusion guidance.

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