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 still adds real context: no account required, results are official BOE data, the returned discount is computed by BOE arithmetic, and the result set is capped at 15.

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 dense sentence plus two short fragments ('Pública, sin cuenta. Máximo 15.'), front-loaded with the resource and its key qualifier. Minor redundancy in repeating 'Máximo 15' from the schema, but no wasted sentences.

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 an output schema present, return-value documentation is unnecessary, and the description covers what matters: data source, official-result filter, optional province scoping, public/no-account access, and the 15-item cap. Complete enough for an agent to invoke it correctly.

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 both parameters, and the description mainly restates that provincia filtering is optional and that the cap is 15. Baseline 3 is appropriate since it adds little beyond what the schema provides.

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 resource and scope: latest BOE auctions that have an official result (adjudicadas), optionally filtered by province, returning the hammer price and the real discount over the appraisal. An agent can distinguish this result-set from general search tools, though no sibling is named explicitly.

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 'Últimas subastas ... con resultado oficial (adjudicadas)' — use it when you want closed/finished auctions rather than open listings — and 'Pública, sin cuenta' tells the agent no auth is needed. However, no alternative tool (e.g. buscar_subastas, estadisticas_publicas) is named or excluded, leaving routing to inference.

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