watch_file

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It merely says 'watch for changes' without revealing key behavioral traits: whether it is a blocking/long-running operation, how changes are reported (events, callbacks, return values), or that it can be stopped via stop_watching. This is a significant gap for a tool that establishes a watch.

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 a single, focused sentence that immediately states the tool's purpose. It contains no fluff, is front-loaded with the action and resource, and is appropriately sized for a simple concept.

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?

The tool is a watcher with nuanced behavior (long-running, event emission, stop mechanism), but the description provides none of this context. The existence of sibling stop_watching hints at a lifecycle, but the description itself fails to explain that the watch is continuous, how results are delivered, or when to use ignored/recursive/ignoreInitial. The schema covers parameters but not the tool's operational 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 all four parameters are described within the schema itself. The description adds no extra parameter information. Per rubric, a high-coverage schema yields a baseline of 3, and there is no additional value 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 clearly states the tool's function: 'Watch file or directory for changes'. The verb 'watch' combined with the resource 'file or directory' and purpose 'for changes' precisely describes its use. It also distinguishes itself from sibling tools like read_file/write_file by implying a monitoring role, not a content access role.

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 implies usage for monitoring changes, but it does not explicitly say when to use this tool versus alternatives like read_file or stop_watching. There is no mention of exclusions, prerequisites, or when not to use it. The intended use is inferred from the name and description rather than stated.

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