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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, and 'Lecture seule' merely restates them. The description earns credit elsewhere: 'Indicatif — pose signee et norme PMR priment' discloses that results are non-authoritative and that signed drawings and PMR rules override them, which is a real behavioral caveat an agent needs before reporting a verdict.

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 activation trigger, then thresholds, then input shape, then the caveat — a sensible order with no filler. The rule-code parentheticals (MI-LARGEUR, MI-HAUTEUR, MI-OUVERTURE, MI-QUINCAILLERIE) make the single paragraph dense, but each maps to a distinct check, so nothing is clearly expendable.

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-parameter, nested-object tool with no output schema, the description covers the input shape, the acceptance thresholds, and the non-authoritative caveat. It does not sketch what the check returns (per-door verdict vs. aggregate), which is the remaining gap, but the rule that no output schema exists means return-format coverage is not strictly owed.

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 baseline is 3, but the description goes further by expanding the nested 'scene' object: it lists portes_interieures fields with units (_mm) and enumerates the four legal 'sens_ouverture' values (poussant|tirant|coulissant|va_et_vient), which the schema itself does not constrain as an enum. That is genuine meaning added on top of the structured field.

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 LES PORTES INTERIEURES') and enumerates the exact four checks performed: clear width, clear height, declared swing, declared ironmongery. The scope marker 'second oeuvre / PMR' plus the numeric thresholds (830 mm, 2040 mm) distinguish it plainly from installation-oriented siblings like cao_bim_pose_menuiseries without needing to name them.

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?

Opens with an explicit trigger ('Appelez quand vous devez VERIFIER...') and situates the tool in the PMR / second-oeuvre workflow, which tells an agent when to reach for it. It names no alternative sibling and gives no exclusion conditions, 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.