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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered structurally. The description adds real behavioral context by framing results as user-reviewable options and tying them to a downstream purchase step, though it says nothing about result format or empty-result handling.

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?

Two sentences, zero filler, and the core action is front-loaded before the workflow guidance. Every clause carries information an agent needs to act.

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 read-only search with no output schema and all-optional params, the definition covers what is searched, why, and how results should be handled. The gap is that nothing describes the shape of returned options or what happens when no numbers match, which matters for a tool whose output the agent must present to the user.

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 60%: 'state', 'area_code' and 'contains' are documented, while 'city' and 'limit' are bare. The description compensates by enumerating the four practical filter dimensions (area code, state, city, digits), effectively covering city that the schema leaves undocumented, with only 'limit' left unexplained.

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 opens with a specific verb and resource ('Search local US numbers the user can buy') and immediately narrows the filter dimensions. It clearly distinguishes this lookup step from the sibling spur_buy_phone_number, so an agent knows this is the discovery tool, not the purchase tool.

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 explicitly sequences usage: 'Show the options and let the user pick before spur_buy_phone_number,' naming the alternative and the condition that selects it. It also adds a selection heuristic ('Prefer an area code in the user's market'), which is guidance an agent could not infer from the schema.

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