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

Annotations cover the safety profile (non-read-only, non-destructive, closed-world), and the description adds a non-obvious operational consequence beyond them: the current API key stays scoped to the initial project and the new project must be reconnected before it can be driven. That is exactly the kind of side effect an agent would otherwise miss.

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 what is created, then the key-scoping caveat, then the usage exclusion. No filler, though the final sentence is close to restating the second.

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 and no output schema, the description covers the biggest behavioral trap (key scoping) and one exclusion, which is enough to act on. It stops short of documenting either parameter or what the created workspace returns, so it is adequate rather than complete.

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, yet it only hints that the domain ('hostname') is optional. The required 'name' parameter, its 1–191 character bound, and the 253-character hostname limit are never mentioned, so an agent must open the schema to call this correctly.

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 concrete verb and resource – creating a distinct project with its own site and an optional domain – so the agent knows this is a provisioning operation. It partially distinguishes itself from siblings by warning that new pages or corrections belong to the current project, though it never contrasts explicitly with create_project or create_site_project.

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 one clear exclusion: 'Pour une nouvelle page ou une correction, conserver le projet courant.' That is real routing guidance, but there is no positive when-to-use statement distinguishing this from create_project, create_site_project, or switch_project, leaving the agent to infer the boundary.

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