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

The description goes beyond annotations by disclosing the polling nature of the tool, the expected number of calls (15–25 for Shorts), and the interaction pattern (silent repeated calls). It also clarifies when to stop, which is critical behavioral context that annotations do not cover.

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?

The description is dense but efficient, front-loading the core purpose and then providing essential usage loop instructions. Every sentence contributes actionable guidance, and the structure flows logically from what to do to how to do it.

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?

The description is complete for an agent: it covers when to use, how to call repeatedly, how to handle progress, when to stop, and what to expect (links or progress). It also mentions failure/cancellation handling, making it self-contained for correct usage.

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?

While schema coverage is 100%, the description adds practical advice on the max_wait_s parameter (recommending to leave it empty and providing client-specific defaults). This adds meaning beyond the schema, though job_id is already well-described.

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 clearly states the tool's function: it waits for a video to be ready and returns download links or progress. It distinguishes itself from siblings by explicitly tying it to the creation workflow and positioning it as the polling mechanism for delivering videos.

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?

The description provides explicit usage guidance: it instructs the agent to call this tool repeatedly after kleo_create_video until links are returned, and to avoid stopping or asking the user unless the user requests it or failure/cancellation occurs. This is a clear 'when and how to use' directive.

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