bind_evidence

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

With no annotations provided, the description carries the full burden and does add meaningful behavioral context: it rejects semantic stance, enforces a bounded operation, and explains the rationale (preventing topical attachment from becoming support). However, it does not disclose what happens when quote verification fails, whether state is mutated, or what the response shape is, so transparency is incomplete.

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 compact: the first sentence states the action and scope immediately, and the second justifies the design constraint without excessive padding. The rationale sentence earns its place because it clarifies an otherwise easy-to-miss boundary, though it is slightly longer than strictly necessary.

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 tool is fairly simple and has an output schema, so the description does not need to explain return values. Still, it leaves gaps around the meaning of 'verify quote presence,' the expected format of quotes, and the behavior when a quote is not present in the source. An agent could probably invoke it correctly but might not handle verification failures appropriately without more detail.

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 for the schema. It only indirectly hints at parameters: 'quotations' implies quote, 'existing claims' implies claim_id, and 'source quotations' implies source_id. It does not explain research_id, bindings as a batch, or constraints on the quote string, leaving the agent to infer most parameter semantics from names 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 opens with a specific verb and resource: 'Bind direct source quotations to existing claims and verify quote presence.' It also explicitly disclaims semantic stance, which clearly separates it from entailment-judgment sibling tools like judge_evidence. This leaves little doubt about what the tool does.

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 clear context: use this tool for verbatim quote binding against existing claims, and do not use it for semantic stance or entailment judgment. It does not name the alternative tool explicitly, and it only implies that claims must already exist, but the exclusion is strong and actionable.

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