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

No annotations are supplied, so the description carries the full burden. It does disclose the return payload (dirección exacta, coordenadas WGS84, superficie m², año de construcción, uso principal, enlaces al visor), which is genuine behavioral context, but it says nothing about error behaviour for malformed or non-existent referencias, latency, rate limits, or whether the data is a live official query.

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?

Two sentences, zero waste: the first front-loads what the tool does and the input identifier, the second lists exactly what comes back. Nothing is repeated or padded.

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 one-parameter read-only lookup with no output schema, the description is nearly self-sufficient because it enumerates the returned fields and the coordinate system. The remaining gap is failure behaviour for invalid or unknown referencias, which matters for an agent deciding how to recover.

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 documents the single parameter, its 14 vs 20 character formats, and gives two examples. The description repeats the same 14/20 character distinction and adds no new meaning such as validation rules or how the 20-character cargo/control suffix changes results. Baseline 3 applies.

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 concrete verb and resource: consulta la información física y geográfica de un inmueble o parcela a partir de su Referencia Catastral, in Spain, and enumerates the returned fields. The direction of the lookup (referencia → datos) is clearly the inverse of the sibling coordenadas_a_referencia_catastral, but that sibling is never named, so differentiation is implied rather than stated.

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 only implied: an agent can infer it should call this when it already holds a Referencia Catastral and wants physical/geographic data. There is no explicit statement of when not to use it, nor a pointer to coordenadas_a_referencia_catastral for the reverse case (coordinates → referencia) or to the WMS tool for layers.

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

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

No annotations are supplied, so the description must carry the behavioral load. It usefully discloses the geographic constraint (Spain only) and the nature of the result (cadastral reference plus official address), but says nothing about latency, rate limits, failure modes for out-of-coverage coordinates, or what an empty/no-match result looks like.

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?

One front-loaded sentence that first names the operation and then the outputs, with no filler. It is dense rather than padded, though the phrase 'en cualquier punto de España' and the parenthetical coordinate reminder slightly duplicate information already in the schema.

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 two-parameter lookup with no output schema, the description covers the essential picture: what goes in, what comes back, and where it is valid. The only real gap is that return semantics for no-match cases are unstated.

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% and both parameters already document decimal WGS84 with examples, so the description adds no new parameter meaning beyond restating 'latitud y longitud WGS84'. Baseline 3 applies because the schema does the heavy lifting.

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 a specific operation and resource — 'Geocodificación inversa catastral' returning 'la Referencia Catastral y la dirección oficial' — plus the exact input (GPS coordinates) and geographic scope (Spain). An agent can distinguish it from consultar_referencia_catastral by the inverse formulation, though no sibling is explicitly named.

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 scenario is implied (you have lat/lon and need a cadastral reference or official address), and 'en cualquier punto de España' implicitly bounds where it applies. However, there is no explicit when-to-use/when-not statement and no mention of the forward-lookup sibling consultar_referencia_catastral as an alternative.

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

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

With no annotations, the description must carry the behavioral burden; it does convey that the tool is a read-only reference lookup returning static endpoint specs and layer names rather than live map data. It omits whether the WMS URLs require authentication or API keys, whether the endpoints are stable/canonical, and in what format the response arrives — all material for an integration tool.

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 single sentence front-loaded with the verb and the core return payload, with the integration targets appended as context. It is slightly dense with enumerations but no sentence is wasted.

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 one-parameter, read-only lookup with no output schema and no annotations, the description adequately explains what is returned and for what purpose. The main residual gap is response format and any authentication caveats around the WMS URLs.

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% and the single 'servicio' parameter has a fully documented enum with a stated default, so the schema already does the heavy lifting. The description alludes to the service families (catastro, PNOA ortofotos) but adds no behavior for the enum value 'edificios_inspire' or what changes per selection.

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?

Names a specific verb ('Devuelve') and a concrete resource set: specifications, WMS endpoint URLs and official layers from DGC and PNOA. It is clearly distinguished from the siblings, which deal with cadastral references (consultar_referencia_catastral, coordenadas_a_referencia_catastral), not map service endpoints.

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 implies usage through the target consumers (GIS projects, Leaflet, QGIS, web apps), which tells the agent the scenario the tool serves. However, it never states when NOT to use it or names the sibling tools that handle address/parcel reference lookups instead, so the routing decision is left to inference.

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