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

Annotations flag destructiveHint=true and non-idempotent, and the description supplies the actual reason: a buyer message on a job with a pending close request clears that request and stops the seven-day automatic-release clock. That is substantive side-effect disclosure beyond the annotations. It stops short of describing failure behavior when the recipient is ineligible or whether the recipient is notified.

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 the core action, then eligibility, then the side effect. Every sentence carries information, though the final sentence is dense and could be split for readability.

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 three-required-param mutation tool with no output schema, and the description covers the action, recipient constraints, and the non-obvious close-request side effect. It does not cover what is returned on success or what errors to expect for invalid recipients, which keeps it short of full completeness.

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 all three parameters are already documented. The description adds the eligibility constraint on 'to' (bidder or buyer), which is meaning beyond the schema, but says nothing extra about content or job_id beyond the schema text. Baseline plus a modest bump.

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 ('Send') and resource ('a message on a job') and narrows the recipient to 'a specific other participant', which cleanly separates it from the read-side sibling get_messages. The role-based recipient rules make the action unambiguous.

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 concrete eligibility rules per role: a buyer may only message someone who has actually bid, and a bidder may only message the buyer. That is real when-to-use guidance, though it never names an alternative channel or states when not to message (e.g. use send_request instead).

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