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

Since there are no annotations provided, the description carries the full burden of behavioral disclosure. The description lists the output fields (validity, region, carrier, line type, timezones) and mentions the underlying library, which is useful, but it does not disclose any side effects (it is a read operation, but that's not stated), rate limits, authentication requirements, or error behavior. It also doesn't clarify whether the input is expected in a specific format (e.g., E.164). An agent is left with an incomplete picture of what happens on invalid or international numbers.

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 description is short and front-loads the core purpose, but it crams multiple attributes into a parenthetical list and does not separate the purpose from usage guidance. It is a single sentence that is readable and efficient, but it could be structured with a bit more clarity (e.g., stating 'Look up a phone number' as the verb phrase). It earns an average score because it is concise but not optimally structured for an agent to quickly parse.

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?

The tool has an output schema, so the return format is likely covered there, which partially compensates for the description. However, the description does not explain the input parameter format, any limitations (e.g., does it handle international numbers? does it require a specific country code?), or how the various output fields are derived. Given the tool's complexity and the need to select from many phone-related siblings, the description is incomplete for an agent to call it correctly without looking at the schema and guessing.

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?

The schema has a single parameter 'q' with only a default and no description, so schema coverage is 0%. The tool's description says 'Number Lookup' and lists the attributes returned, implying the parameter 'q' is the phone number to look up, but it never explicitly explains what 'q' represents or its expected format. Since there is no schema description and the tool description fails to define the parameter, the agent is left to infer that 'q' is the phone number. This is a significant gap for a tool with one critical parameter.

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 clearly states the tool's purpose: it performs a phone number lookup providing validity, region, carrier, line type, and timezones. This distinguishes it from the many sibling tools, particularly the generic 'phone' and 'phonefmt' tools, by listing specific attributes it returns. However, it doesn't explicitly name a sibling that it differs from, so I subtract one point.

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 does not provide any guidance on when to use this tool versus alternatives like 'phone', 'phonefmt', or 'phonepivot'. It mentions that it uses libphonenumber, which is a strong hint about its scope, but there is no explicit when-to-use or when-not-to-use, nor any mention of prerequisites or limitations. This lack of context leaves an agent to guess when this is the right lookup among many phone-related tools.

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