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

Annotations declare a non-read, idempotent, non-destructive open-world mutation, and the description adds real substance beyond them: per-value side effects (contact becomes spam, lead work stops, Quo card tagged conditionally on the business's write setting, reengage tags for a later marketing touch) and the fact that the thread itself is not cleared. The conditional tagging caveat is exactly the kind of behavioral nuance annotations cannot express. It stops short of stating permission requirements or what happens on an invalid/non-quiet target.

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?

The core action and its non-effect are front-loaded, and the enumeration of dispositions is compact. The parenthetical on spam is dense and slightly overloaded, but every clause conveys distinct behavioral information.

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 3-parameter required mutation with no output schema, the description covers side effects, the non-effect on the thread, and idempotent retry semantics, which is most of what an agent needs to call it safely. Gaps remain on authorization requirements and on the failure mode when the thread isn't actually quiet.

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 only 33% (only idempotency_key is documented in the schema), so the description carries most of the burden. It does this well for `disposition`, explaining the meaning and consequence of each of the four enum values rather than just repeating them. However, `conversation_id` gets no explanation at all, and the description never says what qualifies as a 'quiet thread' the id must point at.

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 resource ("records why a quiet thread needs no reply") and enumerates the four disposition values with their effects, so an agent knows exactly what the call does. It also explicitly negates the nearest sibling behavior with "It does not clear the thread," separating it from clear/bulk_clear_conversations and set_conversation_status.

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 phrase "why a quiet thread needs no reply" gives a clear precondition for use, and "It does not clear the thread" tells the agent this is not the clear action. It also gives retry guidance via the idempotency_key sentence. What's missing is an explicit named alternative for the case where the agent does want to clear or close the thread rather than disposition it.

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