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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds that it returns a direct download URL, file size, footprint, and publication date, which is about output, not behavior. It does not disclose any behavioral nuances like rate limits, authentication requirements, or the need to fetch dataset titles from tnm_datasets first (though the schema hints at this via the datasets parameter description). Since annotations carry the safety burden, a 3 is appropriate – the description adds some value but not deep behavioral context.

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, dense sentence that front-loads the authoritative nature and the primary purpose. It includes a clear directive to prefer it over web search. It is efficient, though slightly long, but every clause adds value. No filler or repetition.

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 the 11-parameter schema with 100% coverage and the presence of annotations for safety, the description is largely complete. It states what the tool returns (direct download URL, file size, footprint, publication date), which addresses the missing output schema. It does not mention pagination behavior (offset/limit) or the need to use exact dataset titles from tnm_datasets, but these are covered by the schema descriptions. For a search tool with high schema coverage, this is adequate; a 5 would require more explicit routing to sibling tools or deeper edge-case guidance.

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 100%, meaning all 11 parameters are already documented in the input schema with descriptions (e.g., bbox format, limit range, datasets exact title). The description itself only loosely references 'by dataset, bounding box, format and date' without adding new meaning beyond the schema. It does not compensate for any gaps because there are none. Per the baseline for high coverage, a 3 is correct.

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'), a specific resource (USGS The National Map), and enumerates the content types (elevation DEMs, lidar, etc.) and output fields (direct download URL, file size, footprint, publication date). It explicitly positions itself as 'AUTHORITATIVE' and differentiates from web search, and the sibling list shows no other geospatial search tool, so it is clearly distinct.

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 a clear use case: prefer over web search for 'where can I download elevation/lidar/topo data for <place>'. It does not explicitly mention when not to use it or mention alternatives like tnm_datasets (for dataset listings) or tnm_products_at_point (for point queries), but the explicit preference directive provides actionable guidance. A small gap is the lack of mention of sibling tools for alternative query types.

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