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

Annotations already declare readOnlyHint=false, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavior beyond that: it is asynchronous (poll get_research_analysis), completed/partial runs can emit presentations/clips/reels, and uncertain retries should reuse the idempotency key. It does not discuss permissions or rate/budget limits, keeping it below a 5.

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 core purpose, then modes, alternatives, output behavior, and retry guidance in four dense but purposeful sentences. Minor density cost from packing multiple ideas, but no sentence is filler.

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?

Output schema exists, so return values needn't be explained, and annotations plus the polling/retry guidance cover the async lifecycle well. However, for a 12-parameter tool with 8% schema coverage, the description leaves most parameters unexplained, so it is not fully complete for correct invocation.

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 only 8%, so the description must carry parameter meaning, but it only explains the mode enum values and hints at the idempotency key. Ten parameters including codebook, group_by, call_budget, output_type/output_name, parent_run_id, include_synthetic, session_id, and question are left entirely undocumented in both schema and description.

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 scope: 'Start a durable analysis across the session sources', and the four modes are enumerated with distinct purposes (exhaustive, quick, aggregate, explore). It also names the sibling tools it is not (chat_research_session, queue_research_chat, generate_research_output), so an agent can distinguish it from alternatives without opening schemas.

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?

Explicitly routes the agent: 'Prefer chat_research_session or queue_research_chat for questions and generate_research_output for saved outputs', and directs follow-up to 'Poll get_research_analysis'. This provides both when-to-use and when-to-use-something-else guidance.

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