review_candidates

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

No annotations are provided, so the description must disclose behavioral traits. It only says this is the preferred path and describes it as a review, but does not state whether it mutates state, has side effects, or returns anything. The agent is left to infer the tool's impact on the research state.

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 paragraphs, front-loaded with the purpose, and no filler. Every sentence contributes to scoping or usage, making it easy to parse and understand quickly.

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?

The description does not explain the expected format of reviews, what happens after submission, or how to fill the many fields like strength or reason. Although an output schema is signaled, it is not shown, and no behavioral context is provided. This is insufficient for a tool that accepts a batch of complex review objects.

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?

The schema has 0% description coverage, so the description should compensate, but it only vaguely maps 'relevance', 'direct quote', and 'semantic relation' to the fields. It does not explain the meaning of verdict, relation enums, strength, or how to set them. The description adds minimal value over the raw schema.

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 is a unified claim/source review covering relevance, direct quote, and semantic relation. It also differentiates from siblings by naming screen_sources as the pre-claim path and bind_evidence/judge_evidence as low-level alternatives, making the tool's purpose unambiguous.

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 explains when to use this tool: after claim IDs exist, and for both initial evidence and targeted gap evidence. It also names alternatives and deprecates bind_evidence/judge_evidence, giving the agent clear routing logic.

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