update_conversation

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

Annotations only declare the mutation is non-read-only, non-destructive and non-idempotent; the description goes well past that. It discloses that resolving or archiving clears the assignment and returns the thread to the AI, that ai_paused=true reopens a resolved thread, that resume is refused with 409 for solicitation pauses, fraud flags and connected-account pauses (liftable only in the portal), and that status is applied before ai_paused — all behavior an agent could not derive from structured fields.

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?

Front-loaded with the operation, then dense but purposeful detail; every clause about 409 refusals and field ordering earns its place. The sentence "Two optional fields" is redundant with the schema, and the stacked parentheticals make it harder to scan than it needs to be.

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 with no output schema, the definition covers side effects, ordering, and error paths thoroughly. The remaining gap is idempotency: the annotations mark idempotentHint=false, yet the description never explains what happens on a repeat call with the same status or ai_paused value.

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 already 100%, so the baseline would be 3, but the description adds real meaning beyond it: the inbox-button equivalents for ai_paused, the cross-field ordering rule, and the failure conditions for resuming. That is exactly the kind of semantic freight the schema cannot carry.

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 ("Update a conversation") and immediately enumerates the two mutable fields, so an agent knows exactly what surface is touched. It does not, however, distinguish itself from siblings like assign_conversation or get_conversation, which also concern a conversation; the reader must infer that assignment changes belong elsewhere.

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?

Guidance is concrete on when each field applies, mapping ai_paused=true to the inbox Claim button and false to Transfer to AI, and noting that resolving or archiving hands the thread back to the AI. Exclusions are partial: the 409 refusal cases are named, but there is no explicit statement about when to prefer this tool over assign_conversation.

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