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

Annotations declare readOnlyHint=false, idempotentHint=false and openWorldHint=true; the description goes beyond them by disclosing latency ('takes several minutes') and that the call consumes account points at website rates, which matters for a metered operation. It does not restate the non-idempotent/mutation nature of the call or whether repeated calls spawn parallel committees.

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 core content is front-loaded and dense with useful detail, but the trailing parenthetical '(uses points, metered on the models used like the website)' duplicates the earlier 'Uses the account's points at the website's rates', leaving a redundant sentence.

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 long-running, metered job with no output schema, the description covers the key agent-facing facts: what it produces, how long it takes, how to retrieve results, and that it costs points. It stops short of describing failure/retry behavior or how to monitor progress via the sibling list_deep_analyses.

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 enums and per-parameter descriptions for tier, asset, agents, models, horizon and language, so the schema carries the semantics. The description adds only asset-type context (stocks vs crypto committee composition, model overrides) and nothing about tier, horizon or language beyond the schema, so 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 verb and resource (start the deep research committee on a stock or coin) and spells out the committee seats and the deliverable (verdict with entry, stop and target). An agent can distinguish this immediately from sibling get_deep_analysis, which is explicitly named as the follow-up reader.

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?

Gives clear context: it is a multi-minute operation and should be followed with get_deep_analysis, which routes the agent correctly within the async pair. However it offers no guidance on when to prefer this over run_live_analysis, start_autopilot, or ask_deep_analysis, so the alternatives are left implicit.

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