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

Annotations cover open-world/read-only/idempotency flags, and the description still adds material behavior not in them: an ~8s latency budget, the specific refusal reasons and their semantics, and the token cost model (width x height / 750). The token-cost estimate is unusually valuable for an agent planning a call.

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 tight paragraphs: the first gives purpose, latency, and return; the second gives failure modes, an ethics constraint, and cost. Every sentence carries independent weight and the critical scope statement is front-loaded.

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?

There is no output schema, and the description compensates by stating what comes back (metadata plus frame_id plus the image). For a two-parameter open-world capture tool, failure modes, latency, cost, and the ethical constraint leave nothing an agent needs 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 the baseline is 3, but the description earns a bump by tying `size` to a real consequence (440 tokens at 768px) and by naming the returned `frame_id` as the input to show_worker_image. It does not restate the 256-1280 range, which is fine since the schema already does.

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 concrete verb and resource ('asks their page for a still and waits for it') and pins the scope to the worker's live view. It even names the downstream sibling (show_worker_image) that consumes its frame_id, so an agent can separate it from get_worker_location or get_worker without opening a 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 explicit preconditions ('when they are not live') plus the exact refusal codes (interactive_not_live, paused_by_worker, worker_away) and the ethical boundary 'never use a frame to identify or look up people.' It lacks an explicit statement of which sibling to use when a live frame isn't needed (e.g. a cached image), so it falls just short of full alternative routing.

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