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

Annotations already establish this as a read-only, idempotent, open-world lookup, so the description's job is to add the operational detail it does supply: the output shape (resumen, afecciones for site and corridor, sin_cobertura, consultar_tambien, per-layer source and date), the extra legal-band/norma/tramitador fields only present when a street address is given, and the instruction to relay 'resumen' verbatim. That gives concrete expectations about what comes back and how complete it is. It does not discuss latency or the cost of a long corridor (up to 500 points), which is the only remaining gap.

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?

Three clearly separated blocks — coverage, when-to-use, return values — with the trigger condition front-loaded in the second paragraph. The long layer enumeration is verbose but earns its place because it tells the agent what is and is not answerable, reducing false claims. Minor redundancy with the schema on trazado ('Solo con dirección personal de acceso') and the barra_id description.

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, and the description compensates by naming the returned keys, the per-layer provenance (fuente y fecha), the coverage gaps, and the legal disclaimer. Combined with read-only/idempotent annotations and a fully documented schema, an agent has what it needs to call and report correctly. Return-value typing (e.g. geometry vs. text) is left unspecified, which keeps it from a 5.

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%, so the schema already explains radio_m, trazado, barra_id and ubicacion, including that trazado overrides the straight line and that ubicacion accepts an address, municipality, cadastral reference or 'lat, lon'. The description mostly restates these and adds only the framing that the corridor runs straight to the node's substation; radio_m and the shape/limits of trazado are not discussed. Baseline 3 is appropriate when the schema carries the semantics.

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 names the resource precisely — territorial/legal constraints ('afecciones') of a site plus the straight-line corridor to its grid connection node — and enumerates the layers covered (Red Natura 2000, flood zones, hydraulic public domain, public forests, roads/railways, MITECO sensitivity, cadastral/planning class). It distinguishes itself from the capacity-oriented siblings by pointing to buscar_capacidad and ranking_nudos as the source of barra_id rather than duplicating their role. A leading action verb is missing (it opens with a noun phrase), but an agent can still tell what the tool returns.

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?

Explicit trigger: 'Úsala cuando pregunten qué restricciones o permisos afectan a un terreno, a una planta, a una nave o a la línea o acometida hasta la subestación', plus the routing rule 'Para el corredor, pasa el barra_id del nudo elegido'. It also delimits scope via 'sin_cobertura' (patrimonio cultural, calificación detallada) and the disclaimer that it does not replace sectoral reports. There is no explicit 'use X instead' routing for the uncovered topics, so it falls just short of a 5.

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