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

Annotations only declare write/idempotent/non-destructive/open-world; the description goes well beyond by disclosing the asynchronous contract (returns before connection, status `connecting`), the returned fields, that no QR or human is needed, that it never charges, and that a scheduled removal is unaffected. The idempotency annotation is made concrete via the `already_connected`/`already_connecting` errors being framed as success rather than failure.

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 critical constraint (returns immediately, poll get_number) is front-loaded and each paragraph carries a distinct fact: async behavior, cost, scheduled removal, revoked case, idempotency. It runs long with a few near-redundant lines such as "It works the same on every number," keeping it just short of maximally tight.

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 one-parameter restore action with an output schema, the description covers everything an agent needs: async return semantics, which fields come back, how to confirm success, cost, edge cases (removal pending, revoked), and idempotent re-calls. Return-value detail is correctly delegated to the output schema.

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 the `number_alias` description already explains main/alias/id forms and points to list_numbers, so the schema does the heavy lifting. The prose adds only that behavior is identical on every number, which is about scope rather than the parameter itself – baseline 3 is appropriate.

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 and resource ("Reconnect a number that is currently offline") and implicitly bounds it against disconnect_number and get_number by naming the offline state as the precondition. An agent can distinguish it from every sibling without opening a schema.

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?

Explicit when-to-use ("Use it when `get_number` reports `disconnected` and you want to send") plus when-not cases: revoked numbers need a person, and already connected/connecting numbers return specific errors. It also routes follow-up to get_number for polling, so both the trigger and the alternative are named.

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