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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral context: the results are indicative only and the signed DTU 36.5 plus calepinage plan prevail — an important caveat for how an agent should present findings. It still does not say what the check returns (per-pose conformance flags, list of failures), which keeps it below a 5.

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 call trigger, then thresholds, then the scene shape, then the disclaimers — a sensible order with no filler sentences. The single-sentence density with nested parentheses makes it slightly heavy to parse, but nothing is wasted.

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 one-parameter read-only check with full annotation coverage, the description covers the intent, the numeric criteria and the authoritative-document caveat. The remaining gap is the absence of any statement about the return value (no output schema exists), so an agent cannot anticipate the result shape.

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%, but the schema description merely restates the field names, whereas the description attaches acceptance semantics to each: jeu 5-10 mm, seuil <= 20 mm PMR, pattes <= 600 mm, rejingot >= 30 mm, calfeutrement declared. That is real added meaning beyond the structured fields. It stops short of 5 because the units/consumption of the nested array items are only described, not bounded or exemplified.

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 (VERIFIER LA POSE), a specific resource (menuiseries exterieures), the governing standard (DTU 36.5), and enumerates the four controls with rule codes PM-JEU, PM-SEUIL, PM-FIXATIONS, PM-ETANCHEITE. This clearly separates it from adjacent siblings such as cao_bim_vitrages or cao_bim_calepinage, which an agent can rule out from the name-plus-description alone.

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 LA POSE DES MENUISERIES EXTERIEURES" gives an explicit trigger condition, and the enumerated checks imply the scope of the call. However, it never names an alternative tool or an exclusion case (e.g. when to prefer cao_bim_calepinage or cao_bim_dtu instead), so routing among the very large sibling set still requires inference.

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