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

Goes well beyond the annotations by disclosing the concrete side effects available (reconcile number provisioning, resolve an existing provider voice, retry the persisted request with its original idempotency key) and the guardrails (never creates a replacement request, never authorizes new spending). This meaningfully softens and explains the destructiveHint=true flag, though it leaves ambiguous how a destructive outcome could still occur given the 'no new spending' promise.

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?

Four tight sentences with the capability front-loaded and the safety constraints following; each sentence carries distinct information. Slightly dense sentence three stacks three behaviors, but nothing is wasted.

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 an output schema present, return values need not be explained, and the description covers permissions, scope, side-effect boundaries, and the no-op behavior for terminal states. The remaining gap is procedural: it doesn't say how to obtain or validate the operation_id, which matters because it is the only input.

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 0% for the single operation_id parameter, so the description must compensate. It adds useful semantics – the operation must belong to this account and must carry its original authorization grant – but never says where an operation_id comes from or what happens when it is stale or belongs to another account.

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 ('Recover') plus an enumerated resource scope (interrupted number claim, voice clone, subscription attempt) and ownership constraint ('owned by this account'). The framing of resuming an interrupted attempt implicitly separates it from siblings like claim_phone_number and create_voice, which start new operations rather than resume existing ones.

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?

The description makes the trigger condition clear ('interrupted ... attempt') and adds the prerequisite that the original permissions are required, plus the exclusion that completed/definitively-failed operations are returned without action. It does not name a sibling for comparison (e.g., use get_operation to inspect state first), so the alternative-routing is only indirectly conveyed.

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