Capture video

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

Annotations declare destruction and non-idempotency, and the description extends this with concrete operational facts they cannot express: synchronous execution, a required local media runtime, partial capture files on failure, and that recapturing replaces the prior corpus and metadata. That directly explains the destructiveHint and non-idempotentHint in practical terms.

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?

Four sentences, front-loaded with the action and output, then routing, then behavior. Dense but each sentence earns its place; only minor overlap between "Capture one YouTube video" and "Use for a single video," which serves routing rather than purpose.

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 two-parameter write tool with no output schema, the description covers outcome (corpus and file paths), execution model (synchronous, local runtime dependency), failure mode (partial files), and overwrite semantics. Nothing an agent needs to call it safely or set expectations 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 description coverage is 100%, with both url and interval fully documented including range and default, so the schema carries the parameter burden and 3 is the baseline. The description adds no parameter-level detail such as URL format variants or how the screenshot interval affects runtime and output volume.

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 (capture), resource (one YouTube video), and artifact produced (a saved Markdown corpus with screenshots), and explicitly distinguishes itself from uoink_playlist and uoink_url. An agent can identify what the tool does and which sibling to pick 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?

Gives an explicit positive condition ("Use for a single video") plus named alternatives with the conditions that select them (uoink_playlist for a batch, uoink_url for other platforms and long-video modes). When-to-use, when-not-to-use, and alternatives are all present.

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