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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the bar is lower; the description still adds meaningful caveats an agent could not infer — static layers return published locations not live status, pharmacy duty-end times are not guaranteed, and maps_search_url is address search rather than a verified pin. These are exactly the trust caveats that prevent misuse of the results.

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 primary capability is front-loaded in the first sentence and the caveats follow in a compact block with no filler. The remaining lines read as an unordered list of disclaimers rather than being grouped by mode, which slightly hurts scanability but not length.

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?

An output schema exists, so return-value description is not needed, but with eight optional parameters at zero schema coverage the definition should state at least the constraints for radius_m/limit and the lat/lon vs bbox vs district exclusivity. As written, an agent can call it but cannot confidently pick the right spatial arguments.

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 0%, so the description must carry parameter meaning, and it does clarify kind-dependent applicability (bbox/types only valid for city_feature) and what air_quality vs city_feature return. But it says nothing about limit, radius_m, or whether lat/lon must be paired, leaving three of eight parameters undocumented anywhere.

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 opening sentence gives a specific verb and resource ('Find city services by kind and coordinates, or parking/pharmacy by district') and even splits the two operating modes. It clearly separates the coordinate-based and district-based lookups, though it never names the overlapping sibling istanbul_city_services_nearby to disambiguate.

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 supplies real conditional guidance — bbox and types apply only to city_feature, and district lists are the alternative path without distances. However, it gives no guidance on when to pick this tool over its many near-identical siblings (istanbul_city_services_nearby, istanbul_mobility_nearby), leaving the main selection decision to inference.

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