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

Annotations already declare mutation, idempotency, and non-destructiveness, so the bar is lower; the description still adds real value by disclosing that close/reopen/mute propagate to WhatsApp and then sync the database, and that the resulting state is returned. The explicit "never sends messages" reassurance is a useful behavioral constraint beyond annotations. It does not cover permission requirements or what happens to in-flight state on reopen.

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 dense sentences with no filler: the action inventory comes first, the side-effect scope second, and the negative guarantee last. Every clause carries information an agent needs.

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 three-parameter mutation tool with an output schema, the description supplies the action semantics, the conditional requirement, and the external write path, which is enough to call it correctly. It omits permission prerequisites and whether mark_read/mark_unread also sync remotely, a minor gap given the output schema covers return values.

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%, so the description has to carry parameter meaning, and it does partially: it defines the six action values, notes close means archive, and flags the mute/duration dependency. However, conversation_id format and the unit/limits of mute_duration_minutes (max 40320, i.e. 28 days) are left entirely to the schema, so it does not fully compensate for the coverage gap.

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 a specific verb and resource ("Change conversation state") and then enumerates every valid action, so an agent knows exactly what the tool mutates. The parenthetical "(archive)" disambiguates "close" from closing a conversation in the messaging sense, and "This tool never sends messages" separates it from siblings like draft_reply or set_typing.

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 states the conditional dependency that the mute action "requires mute_duration_minutes", which is the main selection hazard among the six actions. It also implies when the tool has real effect (close/reopen/mute write through to WhatsApp). It stops short of naming an explicit alternative tool for adjacent needs, but the action list is self-routing.

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