Vérifier la langue

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety is partly covered; the description still adds real context by naming the engine (LanguageTool LOCAL) and noting it is started automatically, which tells the agent a local process may be spawned. The closing 'Ne modifie rien' reinforces, and is consistent with, the read-only annotation. It does not discuss runtime, failure modes or what happens if the local engine cannot start.

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?

Two compact clauses with the core capability front-loaded and the non-mutation guarantee at the end. No filler, though the style-analysis parenthetical is somewhat dense and could be formatted more legibly.

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 5-parameter tool with one required argument and an output schema, the description should at minimum clarify the text-vs-section input modes and the language parameter's effect; it does neither. It is adequate on what the tool does and its non-destructive nature, but not on how to select inputs 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 only 20%, so the description carries most of the burden, and it does not. It never explains project_id, section_id, revision_id, or the fr/ru/en language enum, nor how text and section_id interact when both are supplied. Only indirectly, via the 'instead of a section' phrasing in the schema, is the text/section dichotomy understandable.

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 states a specific verb and resource set: it checks spelling, grammar, punctuation via LanguageTool and additionally analyzes style (long sentences, repetitions, vague phrasing). That is far more specific than the bare name 'check_language'. It does not, however, distinguish itself from siblings such as check_formatting, check_consistency or correct_academic_section.

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 rather than stated: the tool is for inspecting text quality without changing it, and the schema hint about free text 'instead of a section' suggests the two input modes. There is no explicit when-to-use guidance, no exclusion of the neighbouring check_* tools, and no mention of when correction (correct_academic_section) should be preferred over mere checking.

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