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

With no annotations provided, the description carries full disclosure burden. It reveals key behaviors: immediate return of sessionId and referenceCode, asynchronous completion requiring polling, and inclusion of 2 free revision turns. It also implies human involvement and a 60-minute working session, setting expectations around latency. It does not mention costs or failure handling, but the critical behavioral traits are well covered.

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 three well-structured sentences: purpose and deliverable, immediate return and polling instruction, and revision policy. Every sentence adds actionable information with no repetition or filler. Key details are front-loaded, making it easy for an agent to quickly grasp the tool's 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 complex asynchronous tool involving human experts, the description covers the essential workflow: what the session does, what is returned immediately, how to retrieve results, and how to request revisions. It correctly names relevant sibling tools (get_result, request_think_tank_revision) and gives enough context for an agent to select and invoke the tool without seeing the output schema in the description. The external output schema exists to handle return structure, so the description is sufficiently complete.

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?

The input schema already provides thorough descriptions for all four parameters (100% coverage), so the baseline is 3. The tool description itself does not add parameter-specific meaning beyond what the schema states, though it gives high-level context that the inputs will feed a human expert session. Schema is doing the heavy lifting, so no additional credit is warranted.

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 clearly states the tool's function: convening a 60-minute think tank session with vetted human experts and returning synthesized directions, ideas, and next steps. It distinguishes from sibling order_think_tank_session_30 by explicitly specifying the 60-minute duration, and from other consultation tools by describing the curated team and structured deliverable format.

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 provides explicit workflow guidance: poll get_result with the returned sessionId or referenceCode, and use request_think_tank_revision for the 2 included revisions. It does not directly compare this tool with the 30-minute variant or other expert services, but the asynchronous workflow and revision path are clearly laid out, giving the agent actionable next steps.

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