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

The annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds two useful behavioral facts beyond that: the target project must already exist and belong to the user, and the purpose is to work on that project's site. It does not say whether the switch affects subsequent calls, whether it can be undone, or what a failure looks like.

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?

A single sentence of roughly twenty words, with the action front-loaded and the dependent tool parenthesized inline. Nothing is redundant, though the trailing 'pour travailler sur son site' is the least load-bearing clause.

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 tool with no output schema and clear annotations, the description supplies the essential pieces: what changes, which values are valid, and how to discover them. Missing only the effect on the session going forward and error conditions, which are minor for this complexity.

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 single 'projectId' parameter is documented nowhere in structured data. The description partially compensates by stating it must be an existing project of the user and pointing to list_projects as the source of valid values, but it gives no format or identifier guidance beyond that.

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 states a specific verb ('Basculer cette connexion') and resource ('autre projet existant de l'utilisateur'), making clear it re-points the active connection to a different existing project. It also differentiates itself from list_projects by treating that tool as the discovery step rather than a duplicate. It falls short of 5 only because 'connexion' is never defined.

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?

Referencing '(list_projects)' implicitly tells the agent to enumerate projects first and that the target must already exist, which is genuine routing guidance. However, there is no explicit statement of when not to use it, what happens if the project does not belong to the user, or whether a current active project is required.

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