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

Annotations already declare readOnlyHint and idempotentHint, so safety is covered; the description adds genuine value by disclosing that the response aggregates the file/listing data, computes a minimum cost with ITP and a municipal €/m² comparison, and includes price history and copies in other sources. It does not cover failure modes (unknown id, malformed URL) or latency, but the aggregation behavior is the key disclosure an agent needs.

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: the first front-loads what the record contains via a compact enumeration, the second gives the accepted identifier forms. It is dense but every clause names a distinct part of the payload; no filler.

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?

With one parameter, no output schema and read-only annotations, the description carries its weight by enumerating the returned sections, so an agent knows what to expect without a response schema. Minor gap: nothing about behavior for nonexistent or malformed ids.

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 id parameter is already documented with its 'fuente:referencia' or URL form. The description reinforces this with concrete examples ('boe:SUB-JA-2026-123456', 'solvia:12345'), which goes slightly beyond the schema by showing real source prefixes an agent can pattern-match.

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 ('la ficha completa de una subasta o de un piso de banco') and enumerates exactly what the record contains: expediente/listing data, description, notices, minimum cost with ITP, €/m² bank comparison, price history and cross-source copies. That scope makes it obviously distinct from the search/market siblings without needing to name them.

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 by accepting a single id or a pisoradar.es URL, so an agent can infer this is a single-record detail lookup rather than a search. However, it never states when not to use it or points to siblings such as buscar_viviendas for obtaining the id in the first place, which is the natural prerequisite here.

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