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

Annotations already provide readOnlyHint and idempotentHint, but the description adds valuable context: data source (EEA 2022), ranking method (population-weighted average Lden), and explicit coverage gaps. This goes beyond what annotations offer.

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 paragraph of 4 sentences, efficiently packing essential details. It front-loads the most common queries and then provides data context and usage. Slightly longer than minimal but still concise.

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 tool's complexity (3 optional parameters, no required, output schema present), the description covers all needed context: data source, coverage, usage patterns, and ranking methodology. The output schema presence reduces the need to explain return values, and the description is sufficient for selection and invocation.

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?

Although schema coverage is 100% with descriptions, the additional text explains that 'city' provides detail, while 'country' and 'limit' are for ranking, and clarifies the default limit (10). This adds meaning beyond the raw 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 clearly states the tool answers specific queries like 'how loud is Paris' and 'noisiest cities in Europe', and distinguishes itself by specifying 'Measured (not estimated) noise for 314 European cities' from the EEA. This differentiates it from sibling tools like get_us_city_noise_exposure or get_address_noise.

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 explicit usage: 'Pass a city for detail, a country and/or limit for the ranking.' It also clarifies coverage exclusions (UK, Greece, Hungary). However, it does not explicitly state when not to use this tool versus alternatives, such as for US cities or estimated noise.

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