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

Annotations already declare readOnlyHint and idempotentHint, so the description doesn't need to restate safety. It adds valuable behavioral context: the specific cities where arrondissements are included, and the known coverage gaps. This goes beyond the schema and helps an agent predict failures.

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 three sentences: the first defines purpose and output, the second gives a usage directive, and the third notes exceptions. It is efficient and front-loaded with the core definition. The third sentence is a useful aside but slightly tangential, so it isn't perfectly lean.

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 read-only tool with two well-documented parameters and an existing output schema, the description covers everything an agent needs: core function, intended use, and known data gaps. The mention of specific cities and exceptions makes it exceptionally complete.

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?

Both parameters (lat, lng) are fully described in the schema with ranges and units ('Latitude, in degrees.'). The description only adds the generic term 'coordinates' and does not provide additional format details, bounds, or examples. With 100% schema coverage, the baseline of 3 is appropriate.

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 returns the commune containing a point, with specific fields (names, type, parents, population) and even city-specific arrondissements. It also distinguishes from siblings like communes_near and get_commune by focusing on point-to-commune mapping.

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?

It gives an explicit use case: 'Use it to turn coordinates, from a map or a device, into a commune.' It also highlights known edge cases where no commune exists (Sidi Mohamed Benmansour, 88 km² between Ifrane and Boulemane), which is useful for setting expectations. However, it does not explicitly contrast with alternatives like communes_near, so it misses the 'when-not-to-use' guidance.

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