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

Adds context annotations cannot convey: the message reaches a human support person, so tone/content matters, and the email channel is an equivalent path. This complements readOnlyHint=false and idempotentHint=false without repeating them. It stops short of saying what is returned after the reply or whether the request stays open.

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?

Two tight sentences, imperative and front-loaded: purpose first, then the human-facing caution and the channel equivalence. No filler.

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?

No output schema exists, so the description carries the burden of the post-call picture; it covers purpose, precondition (own open request), and consequence (reaches a person), but is silent on what the caller gets back or whether the request status changes.

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 description coverage is 100%, so both parameters are already documented with format hints (e.g., 'RL-7Q4M2X'). The description reinforces that the reference must belong to one of the user's own open requests and that the message should be the user's own words, but adds no syntax or constraint detail beyond the schema.

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 ('add what the user wants to say') plus a precisely scoped resource ('one of their own open support requests, by its reference'). The 'open' + 'their own' qualifiers separate it from open_support_request and support_status, though no sibling is named explicitly.

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 an actionable operating rule — ask the user first and send their words verbatim — and clarifies the channel: replying to the support email is an equivalent path that lands on the same request. There are no explicit when-not-to-use conditions, but the 'own open requests only' scope in the first sentence effectively excludes closed or other people's requests.

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