Gather evidence and judge sufficiency

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

The description discloses behavior beyond annotations: it runs one corpus search per angle, decomposes tasks, returns coverage status, evidences spans, next queries, and supports draft checks. It explains billing (len(queries) for one-shot, max_total_queries for iterative) and constraints. Annotations readOnlyHint true is consistent with 'without the tool writing the answer'. No contradiction.

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 somewhat lengthy but well-structured: opening with purpose, then parameter explanations, then additional notes on billing and output. It front-loads the core use. Some redundancy (billing mentioned twice) but generally efficient for the complexity (11 parameters). Score 4.

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, the description covers all necessary aspects: what it does, how it works, parameter usage, billing, optional features (requirements, draft), and what returns (coverage status, evidence spans, next queries). The output schema exists, so return values need not be fully detailed, but the description still gives a good overview. Complete and actionable for an AI agent.

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?

With 73% schema coverage, the description adds value by explaining parameter semantics (e.g., task drives decomposition, queries each run a search, max_iterations default and behavior, draft usage). It provides context beyond schema descriptions, but the schema already includes basic descriptions. The description enhances understanding, justifying a 4.

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 purpose: to assess sufficiency of gathered evidence for a multi-part research task, distinguishing it from siblings like search_papers or extract_from_papers. It specifies the action (gather evidence and judge sufficiency) and the resource (evidence), meeting the 5 criteria.

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 when-to-use guidance: when needing to know sufficiency, what is missing, and what to search next. It contrasts with not using it for writing the answer, implying the agent writes the answer. It also describes typical workflow and optional parameters. However, it could be more explicit about when not to use (e.g., simple search). Clear but not exhaustive.

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