watch

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

With no annotations, the description carries the full behavioral burden. It does disclose meaningful traits: event-driven detection ('the moment it lands') and statefulness ('diff it against the last one seen'), implying a stored baseline. But it omits whether watch_start blocks, where watch state persists, what happens if started twice, and what each action returns.

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 core purpose is front-loaded and the workflow/action list follows in a single compact paragraph. The opening fragment 'Close the round-trip' is slightly promotional, but overall there is little waste.

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 four-action dispatcher with a nested args object and no output schema, the description covers the overall purpose but leaves the individual action semantics and returns unexplained. An agent still lacks enough to invoke watch_status or watch_pull confidently, though the high schema coverage partly compensates.

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 enum action values and the nested args object are already documented, giving a baseline of 3. The description repeats the action names without explaining each action's arguments or behavior, so it adds no meaning beyond the schema.

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 names specific verbs and a resource: watch the Final Cut Pro export folder, detect XML on landing, and diff it against the previous version. It also enumerates the four actions (watch_start, watch_status, watch_stop, watch_pull), so an agent can tell what capabilities it exposes. It references the sibling workflow (deliver.push_to_fcp) but does not fully differentiate itself from the other siblings like preview or inspect.

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?

It gives clear context for use: 'Pair with deliver.push_to_fcp for a full loop: push in, edit, Cmd-E, watch_pull', which tells the agent when this tool belongs in a workflow. However, it offers no explicit when-not-to-use guidance and no exclusions relative to alternatives.

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