Remove a watch

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

With no annotations to fall back on, the description carries the full burden of behavioral disclosure. It explicitly warns that the entire price history is permanently deleted and cannot be recovered, and that re-adding starts empty. It also states that a key matching no watch is refused, which is an error-handling behavior. These details go well beyond the basic 'remove' action and are critical for an agent to understand the destructive side effects.

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 three sentences, each earning its place: it states the action, discloses the irreversible consequence, and notes the error condition. The most important information (that this is a removal) is front-loaded, and there is no redundant or fluffy language. It is concise yet complete.

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 destructive operation, the description covers the key contextual points: what it does, the irreversible effect, and the error case. It does not describe the success return value or any permission requirements, but given the tool's simplicity and lack of output schema, these are minor gaps. The description is sufficient for an agent to use the tool correctly in most scenarios.

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 input schema already provides 100% coverage for both parameters ('id' and 'url'), with descriptions indicating when to use each. The tool description simply restates 'by watch id or URL' without adding new meaning such as precedence rules if both are provided, or what happens if neither is given. Since the schema is thorough, the description adds minimal extra value, justifying a baseline of 3.

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 clear verb ('stop tracking') and a specific resource ('one item'), and clarifies the input mechanism (by watch id or URL). It differentiates from siblings like watch_add and watch_list by explicitly framing this as a removal action, so an agent can easily distinguish the tool's purpose without inspecting the schema.

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 explicit context: 'Call this tool to stop tracking one item,' which tells the agent when to invoke it. It doesn't list alternatives or exclusions, but the purpose is unambiguous and the sibling names make the distinction obvious. The mention of 'by watch id or URL' also specifies the acceptable input methods, which is useful guidance.

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