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

Annotations already declare this is a non-destructive, non-idempotent, open-world write; the description adds substantive context beyond that: the list is asynchronously CASS-standardized, so the caller must poll for a status rather than assume readiness, and the call creates data only with no mailing or charge side effects. This is exactly the kind of post-call behavioral knowledge annotations cannot convey.

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?

Four compact sentences with zero filler: the write nature and scope come first, then the polling workflow, then the side-effect disclaimer, then the endpoint. Each sentence contributes 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?

With no output schema, the description compensates by telling the agent that the created list has an id, that the id is needed downstream, and that readiness is signaled by status 3 on a separate tool. That is sufficient for an agent to both call this and act on its result.

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 50% and the description says nothing about the required 'name' parameter, nor does it explain address-field requirements beyond restating the 500 cap already encoded as maxItems. The nested per-field descriptions in the schema carry most of the semantics, so the description only marginally adds value.

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 an explicit verb+resource pair ('WRITE: upload a recipient address list') and adds scope ('up to 500 addresses') and the backing endpoint (POST /molpro/addressLists). An agent can immediately distinguish this from click2mail_get_address_list or click2mail_create_job.

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 lays out the full workflow: create the list here, poll click2mail_get_address_list until status 3, then pass the id to click2mail_create_job. It also states the negative condition that nothing is mailed or charged, which separates it from job-creation tools.

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