manage_conversation

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

No annotations are provided, so the description carries full burden. It discloses the asynchronous queueing behavior, immediate server response with status, polling with get_workflow_result, duplicate-work risk on retry, and detailed pendingReason semantics (queued vs outsideWorkingHours). This goes far beyond a simple 'perform action' statement.

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 description is dense but not bloated; it front-loads the core action, then provides necessary workflow details in a structured manner. It could be tightened in places (e.g., 'may take several minutes' and later 'within minutes' could be condensed), but every sentence earns its place given the complex async behavior.

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 tool with no output schema, the description thoroughly explains the initial status response, how to get the final result via get_workflow_result, and edge cases including outsideWorkingHours. It provides enough to use the tool correctly end-to-end, including error/retry guidance. The complexity of the async workflow is fully covered.

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 100% with descriptions for both threadId and operation. The description adds minor context (e.g., threadId is 'as returned by get_inbox') but does not materially enrich schema semantics. Since schema already documents both parameters, a baseline 3 is appropriate.

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?

Description clearly states the tool's purpose: 'Archive, star, or mute a conversation thread by threadId' and lists the specific operations. It distinguishes itself from siblings like get_conversation (read-only) and send_message (messaging) by specifying the management actions and the input source (threadId from get_inbox).

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 explicitly tells when to use the tool (when you have a threadId and want to archive/star/mute/unmute), and critically explains the asynchronous workflow: do not retry while a workflow is running, use get_workflow_result to retrieve the result, and handle pendingReason scenarios. This is clear, actionable guidance as good as alternatives.

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