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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description's 'Lecture seule' merely repeats that. The value-add is 'Indicatif — bilan frigorifique signe prime', which tells the agent the findings are advisory and not a substitute for a signed calculation — important context beyond the annotations. Return format is still unstated.

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?

Front-loaded with the trigger and the check scope, then the input shape, then the caveat — a sensible order in one dense block. The trailing 'scene : vrv {…}' restates the schema description and is mild redundancy in an otherwise telegraphic, waste-free definition.

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 single nested-object parameter with full schema coverage, annotations for safety, and no output schema, the description is nearly sufficient: it names what is checked, the accepted fluids, and the indicative nature of results. A hint about what the check reports back (per-code pass/fail) is the only notable 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?

The schema already documents the single 'scene' object at 100% coverage, but the description adds real meaning: indoor units must be >= 1, refrigerant must be R32 or R410A, and each sub-field maps to a specific check code. That constrains input values in a way the schema does not.

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 ('VERIFIER LE SYSTEME VRV/DRV (MEP)') and enumerates the exact components checked with their codes (VR-UNITE-EXT, VR-UNITES-INT, VR-FLUIDE, VR-RECUPERATION). An agent can distinguish this from neighbouring MEP siblings such as cao_bim_cvc or cao_bim_climatisation_gainable without reading the schema.

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?

'Appelez quand vous devez VERIFIER...' gives an explicit triggering condition, and 'Indicatif — bilan frigorifique signe prime' signals the boundary of the tool's authority (a signed thermal balance supersedes it). No sibling is named as an alternative, and there is no explicit when-not-to-use, so it stops short of a 5.

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