remove_task_watcher

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

No annotations are provided, so the description carries the full burden of safety disclosure. As a mutation (removal), it's implied that this modifies state, but the description doesn't note whether this requires specific permissions, whether it's reversible via add_task_watcher, or what the response looks like. For a simple operation, bare minimum is provided.

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?

A single sentence with no redundant or filler content. Every word earns its place. Ideal conciseness.

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 two-parameter mutation with no output schema and no annotations, this is adequate but minimal. The description clearly states the operation and the schema documents parameters fully. However, it could benefit from noting what the watcher concept means, what happens on failure, or confirming reversibility. For its simplicity, it meets the minimum viable bar.

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%, meaning the schema already documents both parameters (task_id as 'The task ID' and watcher_id as 'User ID to remove'). The description adds no additional semantics beyond the schema. Baseline 3 is correct when the schema carries all the documentation weight.

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 'Remove a watcher from a task' uses a clear verb (Remove) with a specific resource (watcher) and target (task). It distinguishes from sibling add_task_watcher and get_task_watchers clearly. However, it doesn't explicitly state the scope beyond the basic operation, so it doesn't fully differentiate from other watcher-related tools beyond the obvious opposite operation.

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 context (removing a watcher so they stop receiving notifications), but provides no explicit when-to-use guidance or exclusions. There are alternatives in siblings (add_task_watcher, get_task_watchers) whose relationship is obvious but not stated. It relies on the agent inferring appropriate usage.

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