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

Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description adds behavior beyond that — the binding is reused rather than torn down, the call fails with not_retryable on a non-failed trunk, and it is gated on Meta's messaging-tier/business-verification requirement. It does not say what the retry returns on success or how long provisioning takes, but the recovery semantics are well disclosed.

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 action and the reuse-instead-of-reconnect distinction are front-loaded, and the eligibility/error-code detail follows in a single dense sentence. The em-dash parenthetical explaining error 138015 is long but earns its place by defining eligibility; nothing is truly redundant.

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 two-parameter tool with annotations covering idempotency and safety, the description supplies the missing decision-critical context: precondition state, error code, and rejection behavior. Only the success-side outcome is left implicit, which is acceptable given there is no output schema to explain it.

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 coverage is 100% and both parameters already carry descriptions, including the important 'tenant number UUID (from list_numbers) — NOT the trunk id' disambiguation. The description adds no parameter-level guidance of its own, 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?

The description states a specific verb and resource ('Retry provisioning for a FAILED WhatsApp trunk') plus a key mechanism ('reusing the existing binding instead of disconnecting and reconnecting the account'), which distinguishes it from the rotate/reconnect path a sibling would offer. The uppercase FAILED and the identifier number_id context make the target unambiguous.

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 explicit eligibility conditions: this is the recovery path for Meta error 138015, retry only 'once eligible', and it is rejected with not_retryable unless the trunk is in 'failed' state. What is missing is an explicit named alternative for the other case (e.g. rotate_whatsapp_trunk when the trunk is not failed), so the agent must infer it from the 'instead of disconnecting and reconnecting' clause.

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