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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the mutation risk is known. The description adds genuinely useful behavior: automatic conversion into editable elements, the concurrency-refusal rule ('Une modification concurrente pendant la conversion est refusée'), and the live-vs-draft application semantics. It still omits what is returned and whether the insert is reversible/undoable, which matters for a destructive tool.

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 core action and outcome, then constraints, then versioning. Every sentence carries information relevant to correct invocation, though the dense run-on phrasing and missing mention of the third enum value show minor trimming/structure issues.

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 5-parameter destructive mutation tool with no output schema and zero schema descriptions, the description covers the essentials an agent needs: prerequisites, HTML shape rules, placement, mode semantics, and concurrency failure. It falls short only on the unmentioned 'live' mode value and on what happens after the insert (result, editability handoff details).

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?

With schema description coverage at 0%, the description carries the burden and mostly succeeds: it constrains `html` (self-contained, CSS inside <style>, responsive, one <section> per block, no JS needed) and defines `afterSectionId` placement plus the fallback position. It explains `mode` auto/draft but never mentions the 'live' enum value, and it asks for `expectedVersion` even though the schema does not mark it required — a small ambiguity.

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 ('Ajouter à une page existante une ou plusieurs sections ... en HTML/CSS') and adds the crucial transformation detail that the HTML is 'converties en éléments Outil éditables', which distinguishes it from import_html_page or copy_template_section. An agent can identify the tool's outcome without opening 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?

Gives concrete preconditions and sequencing: read describe_page_style first and supply expectedVersion, and explains the placement fallback ('après afterSectionId, sinon avant le formulaire/pied de page'). It also differentiates mode values (auto on a published page vs draft). It does not explicitly contrast with sibling page-mutation tools such as apply_page_changes or import_html_page, so the routing guidance stops short of a full 5.

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