check_answer

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

Adds value beyond the annotations: 'No model is called, and the same input always gives the same result' independently corroborates idempotency and tells the agent the result is deterministic and offline. It also discloses that 'unsupported' verdicts carry the unbacked claims and, where possible, substitute source values — behavior the annotations do not convey. It stops short of describing cost/latency or how partial matches are treated.

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 operation is front-loaded in the first sentence, followed by the outcome vocabulary and the determinism guarantee. Slightly padded by the indented whitespace and a defensive 'where possible' clause, but nothing is genuinely wasteful.

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?

With an output schema present, the description need not detail return values, yet it helpfully names the verdicts and their payloads. Annotations already cover safety and idempotency. What is missing is guidance on source granularity and any preconditions, which for a three-parameter tool is a modest gap.

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 reported as 0%, so the description must compensate and only partly does: it clarifies that the question is optional context whose figures count as supported, and that sources are what the answer must agree with. It says nothing about the 'answer' parameter or how multiple sources are compared, leaving real gaps.

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?

States a specific verb and resource: check each sentence of an answer against the sources it rests on. The three verdict labels ('supported', 'unsupported', 'unchecked') make the output contract unambiguous, and there are no siblings to distinguish from.

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?

Usage is implied by naming the inputs ('an answer', 'the sources it should rest on') and one rule is made explicit (figures stated in the question count as supported). However, it never says when an agent should reach for this tool, nor what to do when no sources exist or a sentence is 'unchecked'.

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