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

Annotations already declare this is a non-read-only, non-destructive, non-open-world mutation; the description usefully adds the authorization requirement (owners, sign-in) and states the blast radius: it does not block the sender and customers can open a new request. That last detail is genuinely decision-relevant, since an agent might otherwise reach for it as a substitute for blocking. It stops short of saying whether a closed conversation can be reopened.

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 short sentences with the permission gate front-loaded where an agent will see it first, followed by scope and then side effects. Every clause carries information; the only minor friction is the run-on list of things it does not do.

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 one-parameter mutation with no output schema, the essential pieces are covered: who may call it, when it applies, where the id comes from, and what it does not affect. Lacking only edge-case behavior (re-closing an already closed conversation, failure modes), which is a small gap for a tool this simple.

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 0% for the single parameter, so the description has to carry meaning for inquiry_id. It does partially by pointing to the inquiries tool as the source of ids, which is more than the bare string type in the schema. It doesn't state the id format or the 60-character cap, so compensation is incomplete.

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 object ("Close one of this business's customer conversations") plus the precondition "after it is handled," which is more precise than the tool name alone. It also draws a firm boundary around what closing is not (not an appointment/order/payment confirmation or cancellation, not a block), so an agent won't confuse it with transactional tools. It doesn't explicitly contrast with a sibling close/archive tool, but no such alternative is named in context.

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?

"Owners only (needs sign-in)" and "after it is handled" give explicit preconditions, and "Get inquiry ids from inquiries" names the upstream source for the single required argument. What's missing is an explicit when-not-to-use or a named alternative for agents who don't want to close but rather mute or reassign a conversation.

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