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

Annotations declare a non-read-only, non-destructive, closed-world mutation, and the description adds value beyond that: the operation is effectively single-instance (never creates a second site) and retry-safe if requestId is reused. It also clarifies the returned projectId identifies the conversation rather than another project, which is genuine output semantics. Missing are permission/auth requirements and any statement about what happens to existing brief content on resume.

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?

Five short sentences, front-loaded with the core (open/resume the unique site conversation) and then constraints in rough priority order. No filler sentences. Slight deduction for mixing languages with an English tool name, which can slow parsing, but every sentence carries 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 mutation tool with no output schema, the description covers the highest-risk semantics: idempotency, requestId retry behavior, siteId validation source, and the meaning of the returned projectId. The notable omissions are the 'name' and 'attachments' parameters and any note about permissions or what resume does to existing content.

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 5 parameters, so the description must carry the load and does for two of them: siteId (must equal get_current_site.site.id) and requestId (reuse after interruption). The required 'name' and optional 'attachments' parameters receive no explanation whatsoever, so meaningful gaps remain against the 0% baseline.

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 gives a concrete verb pair and scope: 'Ouvrir ou reprendre la conversation du site unique du projet courant depuis le brief', which tells an agent this is a create-or-resume operation on a single site project, not a general creator. It also pre-empts confusion with the tool name by stating 'Ne crée jamais un second site'. It stops short of naming sibling alternatives such as get_site_project or list_site_projects, so it is clear but not fully differentiated.

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?

There is real operational guidance: reuse requestId after an interruption, and siteId must match get_current_site.site.id. However, there is no explicit when-to-use/when-not-to-use routing against siblings (e.g. get_site_project for reading, publish_site_project for publishing), so the agent must infer the boundary from the constraint sentences.

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