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. The description adds genuine context beyond that: it is an aggregate snapshot of the whole project, and it should be refreshed after every mutation. It does not explain pagination limits or how the message pages behave, so the addition is real but partial.

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 with no filler; the scope is front-loaded and the sibling reference closes the entry. The first sentence is a comma-heavy enumeration that is slightly harder to parse than a structured summary, 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 only two parameters, no output schema and read-only annotations, the definition is close to adequate. However, since no output schema exists the description should describe the returned shape more precisely; naming categories like 'travaux' and 'propositions' without indicating their structure leaves the agent guessing about what it will receive.

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 carries the full burden for two parameters. 'Conversation paginée' hints that messagePage controls paging of the message list, but the parameter is never named, no page size or bounds are given, and projectId (a UUID) is not explained at all. The compensation is only partial.

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 ('Lire') and enumerates the exact resources returned for a site project: brief, paginated conversation, proposals, jobs, URLs, site and page versions. It distinguishes itself from get_page, which is named explicitly. The only weakness is that the purpose is expressed as a dense list of return contents rather than a single summarizing clause.

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 concrete workflow guidance ('Relire après chaque mutation') and names the alternative for page-level needs ('get_page fournit le document complet d'une page'). It does not state any when-not conditions or say what to do if the projectId is unknown, but the operative rule is explicit.

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