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

Annotations already declare readOnly/destructive=false/openWorld=false, and the description's "Lecture seule" is consistent with them (confirmatory, not contradictory). Beyond the annotations it discloses what the call yields — the 11 market lots with product/implementation clauses, DTU/NF standards, and the attached quantity take-off — and that setting `lot` narrows output to a single lot's note, which is genuine behavioral context given no output schema.

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 output content, then the parameter effect, then safety. The parenthetical list of trades is somewhat long but doubles as a scope definition, so it earns its place; no redundant sentences.

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 2-parameter tool with a deep nested `scene` object, zero required parameters and no output schema, the description covers the produced content well but says nothing about whether `scene` is mandatory, what keys it expects, or the behavior when the call is made without arguments. Adequate to invoke, not sufficient to invoke confidently in edge cases.

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 the baseline would be 3; the description earns the extra point by explaining the operational effect of `lot=code (00-10)`, i.e. that it returns the note for one lot only, which is more than the schema's terse "Optionnel : code du lot seul". It does not say what happens when `lot` is omitted or what shape the `scene` object must take.

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?

Specific verb (rédiger) plus precise resource (CCTP / cahier des clauses techniques particulières) scoped to a scene and its 11 lots, with concrete expected content (clauses produits/mise en oeuvre, normes DTU/NF, quantitatif). It is unmistakably the CCTP generator, but it does not differentiate itself from plausible siblings such as cao_bim_dtu, cao_bim_lots, cao_bim_cde or cao_bim_note.

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 rédiger le CCTP d'une scène" gives an explicit activation trigger, which is exactly what an agent needs to decide to call it. There is no when-not condition and no mention of an alternative tool for adjacent needs (DTU lookup, lot breakdown), so the guidance stops short of full routing.

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