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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint, destructiveHint=false), so the bar is lower. The description adds genuinely new behavior: the run is asynchronous and must be polled until a terminal status, and it discloses which outputs come back. It omits any rate-limit or timeout guidance, which would have pushed this higher.

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?

Two short sentences, zero filler, and the return contents are front-loaded before the polling instruction. Every clause carries information an agent needs.

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?

With no output schema, the description must carry the return contract, and it does name the three key fields (state, verdict, trade plan) plus the terminal-status behavior. It could go slightly further by enumerating status values (e.g., pending/running/done) so the agent knows exactly when to stop polling.

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 100% with only 2 parameters, so the schema already documents analysis_id (from start_deep_analysis) and the include enum. The description adds no syntax, format, or semantic detail beyond what the schema states, so the baseline 3 applies.

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?

Names a specific resource (a deep research run) and enumerates the returned artifacts (state, verdict, trade plan), so the agent knows this is a retrieval/status tool rather than a kickoff. It does not explicitly distinguish itself from siblings like list_deep_analyses, get_deep_thread, or ask_deep_analysis, so the sibling differentiation is left to inference.

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?

'Poll until status is done' is a concrete, actionable usage instruction that tells the agent this is an asynchronous status endpoint requiring repeated invocation. What's missing is routing guidance: no mention of list_deep_analyses to discover ids or get_deep_thread for the full transcript instead of the summary.

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