watch_diagnostics

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

With no annotations, the description carries the full burden. It explains the watcher behavior, actions, language support, and platform-agnostic nature. It does not disclose potential performance impacts or what happens to previous watcher state, but overall transparent.

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 concise with a clear summary of actions and supported languages. It could be more structured (e.g., bullet points for actions), but every sentence adds value with minimal redundancy.

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 no output schema and sibling tools, the description adequately covers actions and supported languages but lacks details on return values, error handling, or edge cases like timeouts or concurrent watchers.

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?

Input schema has 100% coverage; description adds context like 'required for start and scan' for the path parameter, but doesn't add significant meaning beyond what the schema already provides for action and file parameters.

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 it's a real-time diagnostic watcher for monitoring errors, listing actions like start, stop, status, scan. It differentiates from siblings like 'get_diagnostics' and 'scan_project' by focusing on persistent watching, but doesn't explicitly contrast them.

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 explains when to use each action (start, stop, status, scan) and the required path for start and scan. However, it lacks explicit guidance on when NOT to use this tool or alternatives from siblings.

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