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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the bar is lower, and the description still adds two valuable non-annotation facts: it requires explicit human confirmation in chat, and the pending action expires after 30 minutes. It does not say what happens if the code is invalid or expired (error behavior), which keeps it from a 5.

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?

Three short sentences, zero filler, with the core action stated first and the critical confirmation constraint immediately after. Every sentence earns its place.

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 destructive two-phase confirmation tool with an output schema and covering annotations, the description supplies the essential missing piece — the human-confirmation requirement and the 30-minute TTL. Only the failure/expiry error behavior is left unstated, a minor gap.

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?

With a single parameter at 100% schema description coverage ('Código de la acción pendiente (6 caracteres)'), the schema fully documents the input and the description adds nothing about it. Baseline 3 is appropriate when the schema does all the work.

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 states a specific verb+resource: it executes a write that was left pending confirmation ('Ejecuta una escritura que quedó pendiente de confirmación'). This clearly differentiates it from the generic write/execute siblings, though it never names a sibling (e.g. odoo_cancel) to sharpen the contrast.

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?

It gives an explicit and forceful when-to-use ('LLÁMALA SOLO cuando el usuario haya confirmado explícitamente en el chat esa acción concreta') plus a when-not ('nunca por iniciativa propia'), which is exactly the gating an agent needs for a two-phase commit. It stops short of naming the rejection alternative (odoo_cancel), so it isn't fully complete on alternatives.

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