Unwatch

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

The annotations already declare idempotentHint=true and destructiveHint=false, which covers key behavioral traits. The description adds no further context about side effects, error handling, or what happens if the resource is not already watched. It does not contradict the annotations, but it also does not enrich them.

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 concise sentence that covers the action and supported resource types. It is front-loaded and has no wasted words, making it easy to parse.

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 simple unwatch action with only 2 parameters and no output schema, the description is minimally acceptable but leaves gaps. It does not mention side effects (e.g., whether it only affects the current user) or error cases (e.g., unwatching a non-watched resource). More context would improve completeness, but the core action is clear.

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 0%, so the description must compensate. It does enumerate the resource types, but these are already in the schema's enum. The 'id' parameter is not explained at all (e.g., what it refers to or how it is used), and the description simply restates what the schema already provides without adding meaningful parameter semantics.

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 is specific and clear: 'Stop watching an epic, user story, task, issue, milestone, or wiki page.' The verb 'stop watching' is unambiguous and the resource types are fully enumerated, distinguishing it from sibling tools like watch_add and other mutating actions.

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 (you use it when you want to stop watching one of the listed resources), but it does not explicitly state when to use it versus alternatives (e.g., watch_add) or any prerequisites such as needing to currently watch the resource. It is not misleading, but the guidance is only implicit.

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