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

Annotations already establish readOnly/no-destructive/closed-world, so the bar is lower, and the description still adds real behavior: the status state machine (pending, running, done, failed), presence of progress and error fields, and the one-hour expiry on the signed video link. That expiry detail is operationally important and is not in the schema or annotations.

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?

Two very compact clauses with zero filler, front-loading the polling purpose before the completion payload. It is telegraphic in places (the parenthetical tool names) but no sentence is wasted.

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 read-only poller with no output schema, the description usefully enumerates the return shape and the expiry caveat, which is exactly what is otherwise missing. It stops short of stating polling cadence or failure remediation, which would have made it fully self-sufficient.

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 coverage is 100% and the single 'id' parameter is already documented as the jobId returned by the four producer tools, so the schema carries the load. The description reinforces which tools produce the id but adds no format, lifetime, or lookup semantics beyond it.

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 specific verb ('Suivre') and resource ('tâche de fond') and enumerates the returned signals (status, progress, error), which tells an agent this is a job-polling tool rather than a content tool. It does not name the presentation domain explicitly nor distinguish itself from list_jobs or get_site_project_job, but the referenced producer tools (generate_presentation, import_pptx, export) make the scope inferable.

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?

Usage is implied rather than stated: an agent can infer it should poll this after calling generate_presentation, add_voiceover, export_presentation or import_pptx. There is no explicit 'use this instead of list_jobs/get_presentation' routing and no guidance on when to stop polling or what to do on 'failed'.

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