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

Annotations already declare this a safe, idempotent read, so the safety profile is covered. The description adds real behavioral value by enumerating the full state machine ('reading', 'ready', 'failed', 'purchased') and clarifying what each means, including that 'failed' means nothing to buy. It stops short of describing retry cadence or rate limits, but that's a smaller gap against existing 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 tightly packed sentences: purpose and origin first, then the return states. No filler, no repetition of the title, and nothing that fails to earn 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?

For a polling tool with no output schema, the description carries the essential return-value information and links back to the initiating tool. The remaining gaps (obtaining claim_token, polling cadence) are minor given annotations already cover the read-only/idempotent traits.

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?

The single parameter claim_token has 0% schema description coverage, so the description must compensate and only partially does. "A sample started by get_video_sample" implies the token's provenance but never says explicitly that claim_token is the value returned by that call or what format it takes.

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 ("Poll") and resource ("a sample started by get_video_sample"), and explicitly anchors the tool to the sibling that creates the sample. An agent can distinguish it from get_video_sample and get_checkout_link without opening any schema.

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 phrasing "Poll a sample started by get_video_sample" implies the tool is used after starting a sample, and "Poll" hints at repeated invocation. However, it never states when to stop polling, which states warrant a retry, or how it relates to get_checkout_link once the sample is ready.

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