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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint, non-destructive). The description adds genuine behavioral context beyond those: case-insensitive partial-match behavior, the fixed directory size, the data source (worldweather.wmo.int), and that no auth is required. This satisfies the transparency bar without needing to re-state what annotations already assert.

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?

Four compact sentences, each earning its place: what is searched and how, what is returned and why it matters, concrete query examples, and data-source/auth note. The action is front-loaded and there is zero filler or repetition of schema boilerplate.

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 simple 2-parameter read-only search tool with an output schema present and annotations covering the safety profile, the description is complete: an agent knows what to search, how matching behaves, what key field the result contains (city ID), how to chain it into downstream tools, and that no auth is needed. Nothing required for correct invocation is missing.

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% — both query (with examples and length constraints) and limit (default 20, max 50) are fully documented in the schema. The description largely duplicates that ('case-insensitive partial match', query examples) rather than adding new parameter meaning; its only marginal addition is the downstream-purpose context for why the query result matters. Baseline 3 is appropriate since the schema carries the load.

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+resource: 'Search the WMO World Weather Information Service directory of ~2,600 cities by city or country name.' The scope (~2,600 cities) and match semantics (case-insensitive partial match) precisely delimit what it does, and the explicit chaining reference to wmo-weather.forecast and wmo-weather.climate_normals distinguishes it from the downstream siblings it serves.

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?

Provides clear usage context: the returned WMO city ID is 'needed by wmo-weather.forecast and wmo-weather.climate_normals,' which tells an agent this is the prerequisite search step before those tools. It lacks an explicit 'when not to use' (e.g., if an ID is already known), and the referenced tool names are abbreviated versus the actual siblings (wmo-weather.forecast.daily, wmo-weather.climate.normals), so a 5 is not warranted.

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