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

Annotations already cover the safety profile (readOnly=true, destructive=false, openWorld=false). Beyond that, the description discloses the project-to-site-to-domain invariant that governs every other operation and warns against creating a second site, which is genuine behavioral context an agent cannot get from the 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 returned resources followed by the usage rule. The middle sentence is mildly redundant with 'son site unique, son domaine' but reinforces a constraint that matters for correct agent behavior.

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?

There is no output schema, so the description must sketch the return values, and it does so item by item. For a zero-parameter read tool this is close to complete, with only the exact shape of the returned objects left implicit.

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?

The tool takes zero parameters, so the baseline is 4; the description correctly needs no argument documentation and instead spends its words on what the call yields.

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 ('Lire') and enumerates exactly what is returned: the current project, its single site, its domain, its pages and the conversationId. This distinguishes it from list_projects and get_site_project, though it never names a sibling tool explicitly.

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?

'Commencer ici' gives an explicit entry-point instruction, and 'ne jamais créer un deuxième site dans ce projet' states a clear when-not constraint. It stops short of naming an alternative tool for the cases it excludes, which keeps it below a 5.

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