Delete Watch

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

Beyond the annotations (destructiveHint: true), the description discloses the nature of the destruction: deletion is 'immediate and permanent' and 'its delivery history goes with it.' This cascading data-loss warning is precisely the behavioral context annotations cannot convey.

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?

Three sentences, zero waste: core action, irreversible consequence, and alternative routing. The most critical fact (permanence/history loss) is front-loaded in the second sentence, and every sentence earns its place.

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?

Complete for a single-parameter destructive tool: it covers the action, scope, consequences, and the safer alternative, and annotations carry the destructiveness profile. The only gap is unstated failure behavior (e.g., nonexistent or unowned watch_id), which is minor given the strong ownership constraint already expressed.

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?

With 0% schema description coverage, the description must compensate, and it adds a meaningful constraint — the watch must be one the caller owns. However, it never explicitly mentions watch_id or explains where to obtain it, leaving that inference to the agent; it partially compensates but does not fully document the parameter.

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 states a precise verb-resource pair — 'Delete a watch you own' — and immediately differentiates from update_watch, which merely deactivates. The ownership scope and permanence make this unmistakably distinct from create_watch, test_watch, and list_watches.

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?

Explicitly names the alternative (update_watch with isActive false) and states the exact condition for choosing it over deletion: when the user wants to stop notifications without losing the config or history. This is textbook when-to-use/when-not-to-use guidance.

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