Skip to main content
Glama
NewsCatcher MCP

NewsCatcher MCP

Official

Cancel a research run

cancel_research
DestructiveIdempotent

Stop a queued or running research run or batch when work was started by mistake or should no longer continue; cancelled runs are not charged.

Instructions

Stop a queued or running research run (or batch). A cancelled run is not charged. Use when the user asks to stop, or a run was started by mistake.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "cancel_research"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idNoThe run to cancel.
batch_idNoOr the batch to cancel.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

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

The description adds a genuinely useful billing fact not present in annotations ('A cancelled run is not charged') plus the state constraint that only queued/running runs are cancellable. Beyond that it is silent on what happens to partial results, in-flight work, or what the response contains, which matters for a tool flagged destructiveHint=true and openWorldHint=true.

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 tight sentences: action and scope first, then the behavioral consequence, then usage triggers. No filler and nothing important is 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 action with annotations already covering safety and idempotency, this is nearly sufficient; the billing note is the key missing piece filled in. The remaining gap is the run_id-vs-batch_id selection rule, minor but directly relevant to invoking it correctly.

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 the schema already documents both parameters, including the 'Or the batch to cancel' framing that the description merely echoes with '(or batch)'. Neither structured fields nor the description clarify that one of run_id/batch_id must be supplied despite both being optional (required=0), leaving a real ambiguity unaddressed.

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

Purpose4/5

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

States a specific verb ('Stop') and resource ('queued or running research run (or batch)'), and adds a state qualifier that tells the agent cancellation only applies to pending/active runs. It does not explicitly name a sibling, but 'Stop' is unambiguously distinct from start_research and get_research in intent.

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?

Gives concrete triggering conditions: the user asks to stop, or the run was started by mistake. No when-not guidance or explicit alternatives (e.g., 'for inspecting a run before cancelling, use get_research') are offered, which keeps it a step below full routing guidance.

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