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

Annotations already establish this as a safe read-only, non-destructive operation, so the description's remaining burden is low, and it adds real value: the full status set, a polling cadence constraint, and what a success payload means (proposalId or a pending question) plus an explicit caution not to announce publication. It does not say what the caller should do on failed/cancelled states, which is the main remaining gap.

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 compact sentences, front-loaded with the core purpose, then polling discipline, then return semantics and a guardrail. Every sentence carries distinct, non-redundant information with no filler.

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 single-parameter polling tool with no output schema, the description supplies the status lifecycle and the shape of a successful result, which is the critical missing structured data. Completeness is slightly undercut by silence on jobId provenance, failure-state handling, and the fact that the description is in French while the rest of the toolset and all parameters are English.

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?

There is one parameter with 0% schema description coverage, and the description never mentions jobId — no hint about where it comes from (presumably the create_site_project response) or that it is a UUID. The name and format make the meaning largely self-evident, so this is a marginal gap rather than a blocking one, but the description does not compensate for the missing coverage.

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 action and resource — tracking a persistent job through queued/running/succeeded/failed/cancelled — which is a specific verb+resource pairing an agent can act on. It does not, however, distinguish this from adjacent status/lookup tools such as list_jobs, get_run, or cancel_site_project_job, and it never anchors the tool to the 'site project' scope named in the title.

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 operational usage rules: poll only after pollAfterMs, and do not announce a publication even on success. That is clear situational guidance, but there is no explicit when-not-to-use or named alternative (e.g., use list_jobs to discover a jobId if unknown), so it stops short of full routing guidance.

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