Steering Wheel

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description is consistent with them: 'likely invented facts (or unsupported by the given sources)' explains why an open-world check is being performed. However, it never says what a run returns (per-sentence spans? probabilities? reasons?) and never explains how the threshold parameter changes the outcome, which matters since there is no output schema. The phrase 'Rewrite only the flagged sentences' is ambiguous about whether the tool rewrites or the caller does, but reads as workflow advice to the caller rather than a mutation claim.

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?

Three short sentences, front-loaded with the core action and followed by the flagged categories and the retry loop. Tight overall, though the parenthetical in sentence two slightly interrupts the flow and could be folded into the category list.

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?

For a 4-parameter tool with no output schema, the description should convey what the agent receives back and how the flag cut-off affects results; it does neither, leaving the agent to infer the return shape. Purpose and iterative use are covered, so it is adequate but incomplete.

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 coverage is 100%, so the schema already documents goal, text, sources, and threshold (including its 0.5-0.95 range and 0.6 default). The description only alludes to 'sources' parenthetically and never mentions the threshold, so it adds no meaning beyond the structured fields; baseline 3 applies.

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?

A specific verb+resource: 'Judge every sentence of a draft against its goal,' followed by the exact failure classes it flags (off-goal, filler, repetitive, invented/unsupported facts). No sibling in the provided list overlaps with this function, so no differentiation is needed and none is missing.

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?

Gives a clear operating loop: check the draft, rewrite only flagged sentences, then re-invoke to confirm. That tells the agent when and how to use it, but there is no explicit exclusion or named alternative for cases where sentence-level judging is the wrong tool (e.g. whole-document structure).

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