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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description adds genuine context beyond them: it does not request or return personal data, and the generated writ leaves name/DNI/address as bracketed placeholders. That is useful disclosure about input expectations and output shape. No contradiction with the readOnly hint, since it generates a document rather than mutating external state.

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?

Front-loaded with purpose, then usage condition, then a guardrail about personal data. Reasonably sized, though the no-personal-data warning is restated three times ('NO están entre sus campos', 'No le pidas esos datos', 'no los escribas'), which costs a little economy.

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 seven parameters and no output schema, the description closes the important gaps: it explains what the tool produces (a writ), which non-parameters it will reject, and the condition that qualifies the tool. Nothing an agent needs to invoke it correctly is missing.

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 every field (anio, numero, organo, remedio, decidido, resolucion, fechaResolucion) is already documented in the schema. The description contributes no per-parameter semantics beyond telling the caller which data NOT to supply, 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+resource: 'Compone el escrito con el que se impugna una resolución firmada por el Letrado de la Administración de Justicia... interpone reposición y, subsidiariamente, revisión'. It carves out a precise niche (resolutions signed by the Letrado, not the juez), which materially separates it from siblings like apelacion_auto_inadmision_contencioso or reposicion_contra_sancion_trafico.

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?

'Úsala cuando el documento lo firma el Letrado y lo que decide no es de trámite (inadmite, deniega, archiva, resuelve el fondo)' gives an explicit condition with concrete examples. It implies the when-not (trámite matters do not qualify) but names no alternative tool, so it stops short of a full routing rule.

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