audit_doings_document_claims

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

With no annotations provided, the description carries the full burden. It discloses core behavior (auditing claims, citation markers, lacking support, optional validation) but omits side effects, permissions, or limitations (e.g., text size constraints, API costs for validation). The basic functionality is clear but not deeply transparent.

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 a single 23-word sentence that efficiently covers the core function and optional feature. However, given the tool's complexity (13 parameters), a more structured description (e.g., listing main actions) could improve readability without adding much bulk.

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 is too brief for a tool with 13 parameters, 0% schema coverage, and no output schema. It fails to explain the validation parameters or the output format (e.g., what an audit produces). The agent needs more context to use the validation features correctly.

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. It mentions two input sources (url or text) and optional validation, but fails to explain the many validation parameters (e.g., validationYearFrom, validationMaxPapers, validationRedTeamMode) or their relationships. This leaves the agent underinformed about how to configure the tool.

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 audits SharePoint document text or raw text for research-checkable claims, citation markers, claims lacking explicit source support, and optionally runs research validation. This distinguishes it from sibling tools like classify_claims (classification) and critique_claim (single claim critique).

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 implies usage for auditing documents with claims but does not explicitly state when to use this tool versus siblings (e.g., critique_claim for individual claims, classify_claims for classification). No exclusion criteria or alternatives are given.

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