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

Annotations only give readOnlyHint=false and idempotentHint=false; the description adds substantial context beyond that: it returns a claim token, nothing is generated or charged, the page check is bounded to two seconds, and the tool blocks up to wait_seconds before falling back to 'reading'. This is exactly the behavioral detail annotations cannot convey.

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 what the sample is, then the polling flow, then the no-charge assurance. Dense with semicolons and clause stacking, but every sentence carries load; only mild tightening is possible.

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 describing the return values (claim token, state 'reading'/'ready') and the async completion path via get_sample_status. An agent has everything needed to call and follow up correctly.

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 the baseline is 3, but the description adds real meaning: it explains that wait_seconds governs the bounded page check and the fall-back to 'reading', and that the sample_page_url supplies brand colours while the direct clip is untinted. Slightly above baseline.

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+resource ('get a sample video ad') and characterizes the artifact precisely as 'a stored, blurred library montage.' It explicitly separates this from the real deliverable ('Your real video is made after you start it'), distinguishing it from the sibling create_video.

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 when-to-use and follow-up routing: if state is 'reading', 'call get_sample_status with the claim token every few seconds until it is ready.' The role of wait_seconds versus polling is spelled out concretely.

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