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

Beyond the annotations it discloses three things the schema does not: the downstream Quo inbox only follows when the business's write setting allows (a partial-side-effect risk), the reply-owed business rule can block the call, and retries must reuse the same idempotency_key. These are exactly the operational traits (blocking rules, external propagation) an agent cannot infer from readOnlyHint/openWorldHint.

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?

Roughly three sentences, front-loaded with the primary action and its two modes, then the blocking rule, then retry advice; nothing is filler. Some phrasing depends on product familiarity ("as the inbox's Done and Reopen do") and the parenthetical aside is informal, slightly cluttering an otherwise tight statement.

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 4-parameter mutation with no annotations covering business rules and no output schema, the description covers preconditions, external side effects, and idempotency well. The remaining gap is that it never says what a successful call returns or how to tell the status actually changed, which matters more here because there is no output schema.

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 only 25% (just idempotency_key), so the description has to carry the load and largely does: it maps status to resolved/new, explains replyOwedOverride as the refusal bypass, and adds retry semantics for idempotency_key. conversation_id is left implicit, which is acceptable given the uuid format but keeps this from a 5.

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?

"Marks a thread done (status resolved) or reopens it (status new)" gives a concrete verb plus resource and pins each enum value to a real product action, so the operation's scope is unambiguous. It does not name any sibling tool (e.g. disposition_conversation, snooze_conversation, close_conversation_flow) to say which one to pick instead, so it falls short of a 5.

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?

The description supplies a genuine usage precondition: a thread that still owes the customer a reply is refused unless replyOwedOverride is true, plus advice to justify that override first. That tells the agent when the call will fail and how to escalate, but it never states when to reach for this tool versus a sibling such as snooze_conversation or disposition_conversation.

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