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 real behavior beyond that: the 100-block batch ceiling, that detail changes response size, and that expectedVersion guards pagination against concurrent edits. It stops short of saying what happens if expectedVersion does not match (error vs. stale data), which is the one thing an agent most needs before a paginated read loop.

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 sentences, front-loaded with the primary batching behavior before the mode qualifiers and the concurrency caveat. Dense but every clause carries information; the only friction is the mixed French/English phrasing against an otherwise English tool surface.

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, non-destructive list tool with no output schema, the description covers the essentials: retrieval modes, batch ceiling, detail granularity and concurrency protection. Missing offset semantics and the expectedVersion mismatch outcome are the remaining gaps, but they are modest given annotations already cover the safety profile.

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 only partially does. It gives meaning to limit (100 maximum), blockIds (an alternative retrieval path), detail (summary vs. full payload size), source ('en tête') and expectedVersion (concurrency), but leaves pageId, sectionId and especially offset completely unexplained.

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 les blocs d'une section') and distinguishes the two retrieval modes (batch pagination vs. explicit blockIds), which is more than a title restatement. It never names adjacent tools like get_page_elements or get_page_structure, so an agent must infer the boundary with those siblings.

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?

Useful mode-selection guidance is present: batch-by-section versus targeted-by-blockIds, and summary versus full detail. However, expectedVersion is described only as a protection mechanism, not as a condition under which to send it, and no alternative sibling tool is named for when this tool is the wrong choice.

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