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

The annotations already declare destructiveHint=true and idempotentHint=true, yet the description adds real value beyond those flags: it says exactly what is destroyed ('revoca el enlace compartido') while what is retained is preserved ('Conserva versiones, datos y originales'), and it explains the first-wins race so the agent knows a failed link may mean another account got there first. The 'Repetir para el mismo propietario es seguro' line reinforces, rather than merely repeats, the idempotency hint with its scope condition.

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?

The purpose comes first and every sentence carries content — race condition, retention, revocation, retry safety — with no filler. The middle sentence 'Conserva versiones, datos y originales; revoca el enlace compartido' is telegraphic and leaves the subject and the exact scope of 'originales' implicit, which slightly hurts readability.

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?

An output schema exists, so return values need not be described, and the description covers the mutation's key risks (first-wins, destructive revocation, idempotent retry). What is missing is the authorization/precondition path — whether the account must be connected and what the failure mode is when another account already claimed the budget — which matters for a destructive write.

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 presupuestoId, version and conversation_id are already documented, and the description adds little for them beyond 'por ID'. 'Conserva versiones' loosely echoes the schema's 'Versión abierta; se conserva al vincular' rather than adding new semantics such as version-format or conflict behavior.

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 and resource: 'Vincula explícitamente el presupuesto público reclamable por ID a la cuenta autorizada', naming both the object (a claimable public budget identified by ID) and the destination (the authorized account). That is enough to distinguish it from read-oriented siblings like consultar_datos_presupuesto or listar_presupuestos, but no sibling is named and the 'claimable/link' concept depends on the user already knowing the domain model.

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 only implied: the schema note 'ID del documento que el usuario decidió vincular' gestures at the trigger, and 'First-wins: otra cuenta puede haberlo vinculado antes' warns about the concurrency case, but the description never states the precondition (must be connected via conectar_cuenta first) or when to prefer this over abrir_presupuesto. The 'Repetir para el mismo propietario es seguro' line does tell the agent it need not guard against retries.

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