watch_start

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

No annotations are provided, so the description is the sole source. It discloses the watching behavior and automatic rendering on save, and mentions notifications. However, it lacks details on idempotency, error handling (invalid patterns), and whether starting a new watch stops previous ones. The return value (presumably an ID) is only implied but not stated.

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 three sentences, each carrying critical information: the action, the automated workflow, and the use case. It is front-loaded with the core verb-resource pair and avoids unnecessary words.

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?

Given the complexity (2 params, no output schema, many siblings), the description covers purpose, workflow, and integration with watch_get_latest. However, it fails to explicitly describe the return value (expected to be an ID for use with watch_get_latest), which is a notable gap for invoking the tool 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?

Both parameters (patterns and props) are described in the schema, achieving 100% coverage. The description does not add extra meaning beyond what the schema already provides, such as specifying that patterns are globs and props are assigned to the component. Baseline score of 3 applies.

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 clearly states the verb 'Start watching' and the resource 'component files'. It distinguishes itself from sibling tools like watch_get_latest (retrieve screenshot) and render_file (manual rendering), making the purpose unique and specific.

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 provides clear context for when to use this tool: 'while editing UI' and as part of a live feedback loop. It also instructs to call watch_get_latest after receiving a notification. It implicitly contrasts with render_file. However, it does not explicitly state when not to use it or list alternatives beyond render_file.

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