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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds genuine value beyond them: results are ordered by walking time and an empty radius triggers a nearest-covered-city fallback rather than an empty result.

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, no filler, with the primary behavior front-loaded and the fallback edge case trailing. Every clause carries information the agent needs.

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?

With no output schema, the description usefully describes the result ordering and the fallback case, and pace/language are covered by schema descriptions. Remaining gaps (limit behavior, how multiple interests combine) are minor for a radius-search tool.

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 only 38% across 8 parameters. The description clarifies that lat/lng anchor the search, that interests/categories act as optional filters, and that radius is a hard cutoff, but it says nothing about limit, ordering ties, or how pace affects walking-time sort.

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?

States a specific verb and resource with its scope: sights nearest a lat/lng, sorted by walking time, filterable by interests/category. This clearly separates it from text-based siblings like search_attractions or recommend_attractions, though no sibling is named explicitly.

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 parenthetical 'for example the traveler's hotel or current position' hints at when to reach for it, and the fallback sentence implies it is safe to call in sparse areas. But there is no explicit when-to-use vs. recommend_attractions/search_attractions guidance and no exclusions.

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