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

Annotations provide readOnly and openWorld hints. The description adds meaningfully: it returns only non-protected data, returns a candidate list for multiple properties, refines with block/stairway/floor/door, and describes the normalized output. No contradictions.

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?

A dense, front-loaded paragraph with zero fluff. Each clause adds actionable information, from the primary use case to the disambiguation behavior and territorial coverage.

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 tool with 9 parameters and an output schema, the description fully covers the decision context: when to choose it, how to refine the address, what to expect in the response, and what's out of scope. The output schema handles return structure, so no additional detail is needed.

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%, but the description elevates the semantics: it explains province/municipality must be by name, streetType is the via abbreviation (CL, AV, PZ), and optional fields serve the disambiguation of horizontal property units. This is exactly the kind of clarification an agent needs to pass correct parameters.

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 opens with a specific verb+resource: 'Resuelve y devuelve los datos catastrales no protegidos de un inmueble urbano español a partir de su DIRECCION'. It clearly distinguishes from siblings by noting it is for when the cadastral reference is unavailable, and references the normalized JSON shared with the reference-based query.

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 explicitly states when to use: 'cuando no se tiene la referencia catastral' and specifies limitations: 'Solo direcciones urbanas' and coverage excludes País Vasco and Navarra. The mention of the reference-based query's JSON implicitly provides an alternative pathway.

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