Dove

Delete watch

delete_watch

Destructive

Permanently removes a specific watch, its stored events, and queued webhook pushes to stop monitoring early. Use the watch ID from creation or listing; this action cannot be undone.

Instructions

Delete one watch of this connection for good, together with its stored events and any queued webhook pushes; this cannot be undone. Use it to stop a watch early (watches also end on their own at expires_at or when their condition is met). Unknown ids and other connections' watches return not_found.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "watch_id": "<watch_id>"
    },
    "name": "delete_watch"
  }
}

Input Schema

Name	Required	Description	Default
`watch_id`	Yes	Watch id from create_watch or list_watches.

Output Schema

Name	Required	Description	Default
`deleted`	No
`watch_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 14, 2026
- addedInput schema / properties / watch_id / description
```
Added value: +"Watch id from create_watch or list_watches."
```
First observedv0.11.0Nov 14, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description goes further by enumerating the collateral damage (stored events and queued webhook pushes), asserting irreversibility, and disclosing the error contract for unknown ids and cross-connection ids. That is exactly the extra context an agent needs before an irreversible call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the destructive scope, followed by usage and then the error case. No filler and nothing repeated from the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a single-parameter irreversible delete with an output schema, so return values need no explanation. Destruction scope, irreversibility, lifecycle context, and the not_found case are all covered, leaving no gap an agent would need to guess at.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and there is a single required watch_id already documented as coming from create_watch or list_watches, so the schema carries the load. The description adds only indirect meaning via the not_found behavior for unknown ids and other connections' watches; the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb plus resource plus scope: 'Delete one watch of this connection for good, together with its stored events and any queued webhook pushes.' It distinguishes itself from create_watch/list_watches by naming exactly what is removed, and the 'of this connection' qualifier prevents confusion with other accounts' watches.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the selecting condition clearly: 'Use it to stop a watch early,' and clarifies that deletion is optional because 'watches also end on their own at expires_at or when their condition is met.' That is a genuine when-to-use/when-not-needed pair, though it stops short of naming any sibling tool as the alternative path.

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