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

Annotations already declare this is a non-read-only, idempotent, non-destructive write. The description adds semantic outcomes per answer (si = keep as the user's rule, no = discard, corregida = accept with rewritten text), which goes beyond the annotations. But it never says what happens to the stored correction after "no", whether re-answering overwrites the prior answer (despite idempotentHint), or what is returned.

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, purpose front-loaded, followed by the safety constraint. Dense but every clause carries info (verb, three answer meanings, text requirement, constraint). Slightly cramped by the nested parentheticals, but 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?

For a 3-param mutation tool with annotations covering safety and no output schema, the definition covers what to do, when not to, and the enum semantics. The remaining gap is downstream effect/failure behavior, which is minor given the annotation coverage.

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?

At 67% schema coverage the description fully compensates: it maps each of the three enum values to a meaning and specifies the condition that requires the optional `text` field ("corregida ... en text"). The schema gives only the enum, not its semantics, so the description adds real decision-relevant meaning.

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+resource: recording ("Apunta") the user's answer to a batch correction, and unpacks what each answer value means. It's clearly distinct from list_corrections or save_correction by describing the act of answering an existing correction, though it never names those siblings.

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?

Includes a strong negative constraint: "Solo con su respuesta explícita, nunca por tu cuenta" — only act on the user's own explicit answer, never guess. That's a genuine when-not rule. It stops short of pointing at alternatives (e.g. list_corrections to stage corrections first), so there's a small gap.

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