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

Annotations already declare readOnlyHint, non-destructive and closed-world, so safety is covered. The description still adds real behaviour the annotations cannot: a hard 300-block ceiling with a 100 default, and the caveat that decorative controls and overlapping elements may appear. It does not explain expectedVersion concurrency or pagination semantics with offset, which are relevant for a versioned read.

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?

Four short, front-loaded sentences with no filler; the return contents come first, then limits, then alternatives. It is tight to the point of being telegraphic, but every sentence contributes information.

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 read-only inspector with no output schema and nine undocumented parameters, the description gives a usable picture of results and the section-local coordinate system, but leaves the version pre-condition and paging/query parameters unexplained. Adequate for safe selection, incomplete for correct invocation.

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% across nine parameters, so the description carries the full burden, yet it only clarifies the coordinate basis (local to the section) and the block limit/default. pageId, expectedVersion, sectionId, query and offset receive no meaning at all, and expectedVersion is required.

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 ('Lire une zone du canevas') and immediately enumerates what comes back (IDs, positions, composants, contrôles décoratifs, chevauchements possibles), which distinguishes it from page-wide inspection tools. It also names the two siblings that cover adjacent needs.

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?

Explicit routing is given: prefer prepare_clone_improvement to analyse the whole page in one call, and use get_page_blocks detail=full afterwards only for the IDs to modify. That is a when-to-use, when-not-to-use, and an ordering instruction, not just implied context.

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