Vérifier la cohérence

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

The annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety and repeatability are known. The description adds real value by enumerating what counts as an inconsistency, but it does not say whether the tool mutates or only reports, what happens when both scope parameters are null, or how findings are scoped. An output schema exists, so return-shape detail is not required.

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 list is compact and every item earns its place, but it is a bare enumeration with no leading verb or framing sentence, and the trailing items (decimal separator, duplicate symbol values) read as an unstructured dump. There is no front-loaded statement of what the tool does or returns.

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 output schema and annotations cover the result shape and safety profile, so the description need not restate them. However, given two undocumented optional scope parameters and no guidance on when to prefer this over neighbouring check_* tools, the definition leaves gaps an agent would need to guess about.

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% for project_id and document_id, and the description supplies nothing about them. Critically, both are optional with default null and the description never explains whether one is required, which takes precedence, or what happens when neither is given — a real ambiguity for a scoped analysis 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 fragment 'Cohérence interne' plus the enumerated checks (figure/table cross-references, numbering, undefined or late-defined abbreviations, field-specific forbidden terms, mixed decimal separators, symbols with two values) makes clear this tool detects internal inconsistencies in a document. It is distinguishable in substance from check_formatting and check_language, though it never names or contrasts with any sibling.

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?

There is no statement of when to use this tool versus check_document_structure, check_formatting, check_language, or audit_references, and no prerequisites or ordering guidance. The reader must infer the usage context entirely from the list of check categories.

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