run_committee

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

The description discloses critical behavior: requires DEEPSEEK_API_KEY, takes 30-90s, returns specific outputs, and caches results from the same day. Annotations confirm idempotentHint=true and destructiveHint=false, and the description adds context about cache behavior and runtime, which annotations do not cover.

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 brief and front-loaded with essential details. However, it mixes Chinese and English, which may reduce clarity for non-Chinese speakers. It is still concise and avoids redundancy.

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?

Given the tool's complexity (LLM committee with multiple roles, caching, API key requirement), the description covers main behaviors but omits parameter details. Output schema exists, so return values are covered elsewhere. Overall, adequate but with gaps in parameter context.

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 0%, so the description must compensate. It only mentions 'force' for cache bypass but does not explain 'symbol' (required) or 'max_rounds'. Without parameter explanations, the agent cannot infer proper values for these fields from the description alone.

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 it runs a 4-role LLM investment committee, specifies the required API key, expected duration (30-90s), and outputs (verdict, confidence, CIO memo). It distinguishes from siblings like 'decisions' and 'explain_decision' by being a specific committee execution process.

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 implies usage for running an LLM committee but does not explicitly state when to use this tool versus alternatives like 'decisions' or 'explain_decision'. It mentions caching (default read cache, force=True to rerun) but lacks context about prerequisites or scenarios where alternatives are better.

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