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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data and "Ne déclenche aucune génération" largely restates it. The description does add genuinely new behavioral context: results are paginated and older entries require walking hasMore. It omits ordering, page size, or what a page of activity contains, which is notable given there is no output schema.

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 resource and its scope, followed by the pagination tip and the no-side-effects note. Each sentence carries information, though the final sentence is close to redundant with the readOnly annotation.

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 one-parameter, non-destructive read tool with no output schema, the description covers scope and pagination direction, which is most of what an agent needs. It remains thin on the return shape (what fields an activity entry has), page size, and ordering, and the description is in French while the tool name and schema are English, adding a small comprehension burden.

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% for the single "page" parameter, so the description must carry the semantics. Mentioning "paginée" and hasMore signals that pagination exists, but it never explains that "page" is a 1-based index with default 1 or how many items a page yields. It compensates only partially for the coverage gap.

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?

The description opens with a specific verb+resource ("Lire l'activité paginée du site courant") and enumerates the activity types covered: requests, responses, proposals, publications and page modifications, including via the editor or MCP. That makes the resource concrete and clearly a read of site-wide activity rather than page content, which distinguishes it from siblings like get_page or list_revisions. It stops short of explicitly naming an alternative tool it supersedes.

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?

It gives partial usage guidance by telling the agent to page through hasMore for older exchanges and files, and it rules out generation side effects. However, it never says when to pick this over neighboring read tools (get_page_stats, list_revisions, get_page_revision, list_conversations) or what the "courant" site scope requires in terms of prior context.

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