stills

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

Without annotations, the description carries the full burden and it does well: it discloses async job behavior, polling requirement, rejection when another job is running, and that stills come from the CLEAN take with no captions/zoom. It could also mention file-writing effects or cancellation behavior, but the core operational traits are clear.

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 compact and front-loaded with the primary action. Every sentence adds necessary information: output format, source take, prerequisites, async response, and rejection behavior. No redundant phrasing.

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 an async extraction tool, the description captures the full lifecycle: what it produces, where, from which source, under what prerequisites, and how to track completion. The output schema covers the jobId return, so the description does not need to restate return values. It is complete enough in context.

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 description coverage is 100%, so the schema already documents both parameters. The description adds contextual meaning around the recorded timeline and output/stills directory, but it does not substantially enhance the semantics of dir or out beyond what the schema provides.

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 states a specific verb ('Extract'), a concrete resource ('recorded take'), a destination ('output/stills/'), and a precise output format ('one PNG per still marker'). It clearly differentiates from sibling tools like render and gif by specifying screenshot mode and the CLEAN take source.

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 gives clear prerequisites ('Needs only a recorded timeline (no key)'), async behavior ('Returns a jobId immediately — poll job_status'), and a rejection condition ('Rejects if another job is running'). It does not explicitly name alternative tools or when to use them instead, but the conditions are strong enough to guide an agent.

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