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

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description adds genuinely non-obvious behavior: no model re-invocation, no quota consumption, honoring pollAfterMs between reads, and that an error does not constitute a finished result. Return shape is left to the output schema.

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?

Four short sentences, each carrying a distinct fact (scope, no side effects, polling rule, error semantics), with the scope constraint front-loaded. No filler, though the sentences are telegraphic and could flow slightly better.

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 handling return values and 100% schema coverage on the two parameters, the description fills the remaining gaps: quota/side-effect behavior, polling cadence, and error interpretation. Adequate for correct invocation.

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%, and the schema itself documents job_id (as returned by duos_crear_consulta) and the response_format enum. The description adds nothing beyond this, so the 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 specific verb and resource ('Recupera únicamente un trabajo propio creado antes'), and the qualifier 'únicamente' plus 'trabajo propio' implicitly distinguishes it from duos_listar_consultas (listing) and duos_crear_consulta (creation). It never names a sibling explicitly, so differentiation is inferable 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?

Gives concrete usage context: only for jobs you created, respectful polling via pollAfterMs while pending, and the warning that an error is not a complete result. It stops short of explicitly steering to alternatives (e.g. what to call to create the job or list jobs).

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