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

Adds substantial context beyond the readOnly/openWorld/destructive annotations: 'Nothing is sent and nothing is kept' (privacy posture), per-section 4000-character cap, 1000-character contact cap, max 3 figures at 200 KiB decoded, and explicit SVG sandboxing rules ('no script, no DTD, href # or data:image/ only'). These are real constraints an agent could not infer from structured fields.

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?

The content is largely necessary given zero schema coverage and no output schema, and it is front-loaded with the purpose first. However the prose is dense run-on semicolon splicing with heavy parenthetical nesting, making parameters and return values hard to scan; a short structured list would have served better.

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?

With no output schema, the description fully spells out the return object: rules, sections array with id/heading/required/state/look_for/questions, next, ready semantics ('the four required sections filled'), filename and base64 pdf. An agent has everything needed to drive the interview loop 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 0%, so the description must carry the full burden and it does: all five parameters are explained with semantics, limits and defaults — sections ids enumerated (envelope, fonctionPrincipale, fonctions, alimentation, format, environnement, production, preferences), contact carved out as non-progress, language limited to fr/en with what it affects, and pdf=true requiring title, plus figure object shape.

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 artifact: 'Draft the specification of the visitor's own project with Picodev's interview', and explains the mechanism (you ask the visitor, the tool says what to ask next and makes the PDF). No sibling tool in the list performs spec drafting, so there is no ambiguity to resolve.

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?

Gives concrete calling guidance: 'Call it with the sections written so far (none at first)' and 'Returns {rules ... follow them}', which establishes the iterative interview loop. It does not name any alternative or exclusion condition, but no sibling overlaps in purpose, so the missing piece is minor.

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