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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real substance beyond them: what is returned (five indices by dimension with figures, profile weights, cut-off date, town count) and the edge-case behavior that towns missing a dimension are listed apart, unranked, with a reason. That edge-case handling is exactly the kind of behavior an agent cannot infer elsewhere.

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?

Front-loaded with purpose, then output content, then the unranked-towns caveat, then the disclaimer – a sensible order. The one cost is the fully duplicated Spanish translation, which doubles length without adding information for a given call, though it is consistent with the tool's bilingual language parameter.

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?

There is no output schema, so the description carries the return-value burden, and it does describe the returned structure and the unranked-edge case. With 4 params at full schema coverage, the remaining gap is minor: pagination or result-size behavior beyond the 'limite' cap is not discussed, but nothing an agent needs to invoke it correctly 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 coverage is 100%, so the baseline is 3. The description earns above that by decoding the enum values the schema only labels as 'Profile id' (family = Family with children, relocation = Moving from abroad, calm = Calm and space) and by explaining that comarca narrows the ranking to one county. It adds semantic meaning the schema does not carry.

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 ('Orders the municipalities') plus the exact input dimension (one profile) and the three concrete profile values. It also signals the output shape (five indices, weights, cut-off date, town count) and explicitly says 'Not a recommendation', which separates it from advisory siblings like calcular_mudanza or comparar_municipios.

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?

Usage is implied: use this when you want towns ranked for a given profile, optionally narrowed to one county. The 'Not a recommendation' note is a useful boundary, but no sibling alternative is named and there is no explicit when-not-to-use condition, so guidance stays at the minimum-viable level.

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