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

Annotations already cover the read-only, non-destructive profile. The description adds genuinely new behavioral context: the exact state values returned (PENDING, PROCESSING, READY, ERROR), the fact that the file URL only appears at READY, and the ownership/auth requirement. It stops short of stating rate limits or whether repeated polling is expected.

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 with no waste: purpose first, then return values, then the auth prerequisite. Every sentence carries information an agent needs.

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 no output schema, the description correctly takes on the burden of describing return values and the READY-only URL. The auth requirement is stated. Only polling behavior and terminal-state handling are left unaddressed for what is otherwise a simple one-parameter read.

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 parameter is already documented as "The id generate_video returned." The description reinforces the ownership constraint ("the API key that owns it") but adds no format or validation detail beyond the schema, so baseline 3 applies.

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 opens with a specific verb and resource: "Read the state of one video you started." The singular "one video" implicitly separates it from the sibling list_videos and the id linkage separates it from generate_video, but neither sibling is named explicitly.

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?

"One video you started" and the schema note that video_id comes from generate_video imply this is a post-generation polling call. There is no explicit statement of when to use this versus list_videos, nor any guidance on polling frequency or when to stop.

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