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

Annotations only cover readOnlyHint and openWorldHint, but the description adds substantial behavior: results are in submission order with an input index for zipping, one bad record fails only itself, suggestions are absent, checks run concurrently against a shared limit, and it requires an API key. It even quantifies latency (~2.6s/100).

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?

Purpose and the record limit are front-loaded, and the sentences carry high information density. The email-latency comparison is mildly tangential but still useful for batch-type selection, so the sizing is close to appropriate.

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 batch tool with no output schema and thin annotations, the description covers ordering, error isolation, auth, concurrency, and latency. It is nearly complete; only the policy parameter's effect on results is left entirely to the schema, which is acceptable.

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%, so the key, phones, and policy parameters are already fully documented. The description's parameter-relevant statements (100 limit, results carry input index, pass key via 'key' field) largely restate what the schema already says, so it adds little new parameter meaning.

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 with scope: 'Verify up to 100 phone numbers in one call.' It also differentiates itself from the other batch types (email being slowest, this being fastest of the three), so an agent can locate it among its siblings 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?

Gives clear context for batch use (100-record limit, per-record failure isolation, no bulk upstream endpoint) and notes a limitation (suggestions unavailable in batch). It does not explicitly route single-number callers to verify_phone, so the alternative-selection guidance is implied rather than stated.

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