Unwatch Directory

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

Annotations already communicate that the operation is idempotent (idempotentHint=true) and non-destructive (destructiveHint=false). The description adds no further behavioral detail, such as what happens if the directory is not currently watched or what the exact return payload looks like. It is consistent with the annotations but does not go beyond them, so a neutral score is appropriate.

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, direct sentence with no superfluous words. It front-loads the action and resource clearly. While it could include a bit more context, the conciseness is appropriate for a simple tool and does not waste any tokens.

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?

This is a simple tool with one required parameter and no output schema. Annotations cover idempotency and non-destructiveness, and sibling tools provide some context. However, the description does not address edge cases (e.g., non-existent watch entries) or clarify the response format, leaving minor gaps that an agent might need to infer. It is adequate but not fully complete for a standalone decision.

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?

The schema describes only the 'directory' parameter as 'Full path to the directory' (50% coverage). The description merely reiterates the role of directory without adding new semantics, and it entirely omits the 'response_format' parameter. With 50% schema coverage and no compensation in the description, the parameter semantics remain under-specified.

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 uses a specific verb ('Remove') and a clear resource ('directory from the watch list'), unambiguously identifying the operation. It naturally distinguishes itself from sibling tools like watch_directory (which adds) and list_watches (which lists), so an agent can immediately understand what this tool does.

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 gives no explicit guidance on when to use this tool versus its siblings. It does not state 'use this when you no longer want to monitor a directory' or mention any exclusions or prerequisites. Usage is only implied by the name and the presence of watch_directory and list_watches in the sibling list, leaving the agent to infer context.

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