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

Annotations only declare the generic write/non-destructive/non-idempotent profile, but the description adds the operationally critical facts: no credits are spent here, credits are spent in the follow-up call at 1 per billable address, concurrency limits of 10 jobs and 50 runs/day, and the account-lock risk of many small jobs. It also names the return value (job_id) and the endpoint. This is exactly the context annotations cannot carry.

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 WRITE marker and the core action, then the critical negative constraint (no verification, no credits), then the follow-up tool, then the rate-limit caution. Dense but every clause carries decision-relevant 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?

A mutation tool with no output schema, but the description still discloses the return value, the credit model, concurrency limits, and the required follow-up call. Nothing an agent needs in order to invoke this correctly is left out.

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 baseline is 3, but the description adds real guidance beyond the schema: the 100-address cap is tied to the tool's contract and the batching rule constrains how the 'emails' parameter should be populated. It does not explain 'filename' or 'leverage_historical_data', which the schema already covers adequately.

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 ('creates a bulk verification job'), bounds the input ('up to 100 e-mail addresses given in this call'), and explicitly distinguishes itself from neverbounce_start_job. An agent knows exactly what this does and what it does not do without opening the 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 explicit sequencing ('run neverbounce_start_job afterwards'), explicit exclusions ('does NOT start the verification and spends NO credits'), and a batching rule ('put ALL the addresses of one list into ONE job') with the account-lock rationale behind it.

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