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

Annotations already declare read-only, idempotent, and non-destructive, so the safety profile is covered; the description adds genuinely new context: the call is free (no credits) and results are capped at 500 per call. It doesn't describe what happens if the job is still running, which is the one behavioral gap.

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?

Three sentences, front-loaded with what is returned, followed by routing guidance and pagination options. No filler and each sentence carries distinct information.

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 results tool with a full output schema and 100% parameter documentation, this is complete: it covers the precondition (completed job), cost, routing versus siblings, and paging behavior. Nothing needed to invoke it correctly is missing.

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 baseline is 3, and the description adds usage context beyond the schema: status filtering is optional and offset is the paging mechanism for large jobs. The 'up to 500 results per call' detail slightly repeats the limit field's max, but the paging/filter framing adds real 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?

A specific verb and resource: retrieves per-address results of a completed verify_bulk job, and names the returned fields (status, sub-status, score). It is clearly separable from verify_bulk (which runs the job) and verify_email (which re-checks a single address).

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?

Explicitly states when to use it ('user needs to know which addresses passed or failed') and when not to ('do not re-verify them with verify_email'), plus the precondition that the job must be completed, which implies check_bulk_status. Nothing is left to inference.

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