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

Annotations only say readOnlyHint=false, openWorldHint=true, idempotentHint=false; the description adds the behavior that actually matters: 20-40 second page reads, the wait_seconds cap, the 'reading' state fallback, and the assurance that nothing is generated or charged by this call. That resolves the tension an agent would feel seeing readOnlyHint=false on a sampling tool.

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 core contract (give URL, get blurred sample + claim token) before the operational detail, and every sentence carries information. The parenthetical describing the sample format is somewhat dense but earns its place by setting expectations for the output.

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 compensates by naming the returned artifacts (blurred sample, claim token) and the state field, plus the follow-up tool and timing. Nothing needed to invoke this correctly or handle its response is missing.

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%, so baseline is 3, but the description explains the runtime meaning of wait_seconds (the tool waits that long, otherwise returns state 'reading') rather than just its type range. The url parameter's role and the reason for the delay are also contextualized.

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 and resource plus the concrete return value: a blurred sample video ad built from a URL, with a claim token. It also names the sibling get_sample_status and the condition for switching to it, so the agent can tell it apart from get_checkout_link and get_sample_status without opening schemas.

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?

Explicitly describes the async flow: call this first, if it returns state 'reading' poll get_sample_status with the claim token every few seconds until 'ready'. It also sets expectations that generation/charging happen later, not here, which tells the agent this is the entry point rather than a one-shot result fetch.

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