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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds real value beyond them: it is a polling endpoint and a failed render refunds montage credits — a side effect an agent would otherwise not know.

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?

Front-loads the returned fields, then the workflow in one sentence, then the refund caveat. The inline argument JSON is redundant with the schema, but everything else is tight and earns its place.

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?

No output schema exists, and the description compensates by enumerating the returned fields. Polling cadence and error/refund behavior are addressed, leaving only the identity of the 'id' parameter underspecified.

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% for the single nested required parameter, so the description should carry the burden. Instead it merely re-serializes the schema as {"path": {"id": "<id>"}} without saying what the id identifies (editing job? project?) or where to obtain 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?

States a specific verb (read/poll) and the exact resource contents: selected sources, measured durations, version, plan, status, result_job_id. It reads as the status/result accessor for an editing job, distinguishable from generic siblings like kelpo_get_job or kelpo_get_project, though it never explicitly contrasts itself with them.

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?

Gives explicit lifecycle guidance: poll this after render_editing and hand the result to video_download. That is clear when-to-use and what-comes-next context. The only weakness is that 'render_editing' is not in the sibling list, so an agent may not be able to resolve that reference.

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