Skip to main content
Glama

Cancel a watch

cancel_watch
Destructive

Cancel a Stacks watch to stop checking a title and permanently delete it, ending notifications. Provide watch_id from list_watches; use dry_run to preview the cancellation without deleting.

Instructions

Stop and permanently delete a watch created with watch_title. TinyFish stops re-checking the title and sends no more notifications. Only watches made by Stacks can be cancelled; get the watch_id from list_watches. Set dry_run to see which watch would be cancelled without cancelling it, for example to confirm with the user first.

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": "cancel_watch"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNoIf true, only report which watch would be cancelled. Nothing is deleted.
watch_idYesThe watch_id from watch_title or list_watches.

Output Schema

NameRequiredDescriptionDefault
titleYes
sourceYesProvenance of the data.
dry_runYes
libraryYes
title_idYes
watch_idYes
cancelledYesTrue if the watch was deleted. Always false on a dry run.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.3

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation risk is known; the description adds real value by spelling out that the deletion is permanent, that re-checking and notifications cease, and that only Stacks-created watches qualify. It does not mention behavior on a repeated or already-cancelled watch_id despite idempotentHint=false, which is the one behavioral gap.

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?

Four short sentences, front-loaded with the destructive effect, then prerequisite, then restriction, then the safer dry-run option. No filler and nothing buried.

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

Completeness4/5

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

For a two-parameter destructive tool with full annotation coverage and an output schema (so return values need not be described), this covers effect, prerequisite, scope limit, and a preview mode. The only omission is what happens when the watch was already cancelled or the caller lacks permission.

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

Parameters4/5

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

Schema coverage is 100%, so both parameters are already documented; the description still adds meaning by explaining why dry_run exists (preview/confirm with the user) and where watch_id originates (watch_title or list_watches). This goes beyond restating the schema types.

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?

The description opens with a specific verb ('Stop and permanently delete') and an identifiable resource ('a watch created with watch_title'), then states the concrete consequence: TinyFish stops re-checking the title and sends no more notifications. An agent can tell this apart from list_watches (read) and watch_title (create) without opening any schema.

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 gives a clear precondition ('get the watch_id from list_watches'), a scope restriction ('Only watches made by Stacks can be cancelled'), and a recommended confirmation flow ('Set dry_run ... to confirm with the user first'). What's missing is a named alternative for the case where the watch is out of scope, but no sibling appears to fill that role.

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