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

Annotations already declare readOnly/non-destructive/closed-world, so the description only needs to add context — and it does: the payload contents, the version appearing at the top, and the fact that 'auto' resolves to the publication when active and the draft otherwise. That fallback rule is real behavioral information an agent cannot get from the schema. Pagination behavior of limit/offset is left implicit.

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?

Three short sentences, front-loaded with the return shape, then the source rule, then the follow-up action — no filler. It would read slightly better if the follow-up pointer were folded into the first sentence, but nothing is wasted.

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 five parameters, no output schema, and 0% schema coverage, the description covers the return shape and the source enum but not pagination limits/defaults or the expectedVersion round-trip. An agent could call it correctly, but it would have to inspect the schema to understand half the surface.

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 parameter burden. It explains the most consequential one, `source`, including the auto-resolution rule, but leaves limit, offset, and especially expectedVersion (an optimistic-concurrency guard, only hinted at by 'version en tête') undefined.

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 concrete verb and resource ('Lire un sommaire paginé') and enumerates the returned content (IDs, noms, nombre de blocs, version en tête), which lets an agent picture the result before calling. It distinguishes itself from get_page_blocks explicitly, but says nothing to separate it from nearby siblings like get_page_structure, get_page_elements, or get_page.

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?

The description gives an explicit workflow: read the outline first, then call get_page_blocks for only the sections to modify, which is genuine when-to-use guidance. It also resolves the ambiguous `source` default. It lacks exclusions (when to prefer get_page or get_page_structure instead), so it stops short of a 5.

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