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

With no annotations, the description carries the full burden and delivers: operations never dial, lines start in test mode limited to test numbers, the gateway pairing code is one-time and expires in 30 minutes, Twilio objects created are tracked and removed exactly on deletion, Twilio bills the account, and sagot lines draw on prepaid balance and cannot receive calls. This is unusually thorough disclosure for a mutation tool.

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?

Front-loaded with the essential facts before provider-specific detail, and each sentence carries information. It is dense and long for a tool description, but little is padding.

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 10-parameter mutation tool with no annotations, no output schema, and 0% schema coverage, the description is remarkably complete on behavior and provider flows. The gap is parameter coverage for edge, callerId, name, and isDefault.

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 0% across 10 parameters, so the description must compensate. It explains provider, accountSid/apiKeySid/apiKeySecret (including that the key must be a Standard API key and is write-only) and numbers, but leaves edge (an 8-value enum), callerId, name, and the explicit isDefault parameter unaddressed.

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 ('Add a phone line from an offered provider') and immediately scopes the operation with behavioral facts ('Adding never dials'). The three provider modes (gateway, twilio, sagot) make clear what kind of line is being created, distinguishing it from siblings like lines_update or lines_list.

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?

Gives substantial context for choosing a provider type and for what happens after creation (test mode, first line default, pairing code flow), and points to collaborators lines.verifyNumber, lines.confirmNumber, lines.twilioNumbers and billing.get. It does not, however, state explicit when-not-to-use conditions or a named alternative tool.

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