Skip to main content
Glama
Ploid MCP

Ploid MCP

Official
by ploidcom

Cancel research

cancel_research
Destructive

Stops an active research run when the user cancels. Completed work and admitted people may still be charged.

Instructions

Stop a research run when the user asks to cancel. Work already completed may still be charged, including people a search admitted before it stopped.

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": {
      "run_id": "<run_id>"
    },
    "name": "cancel_research"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idYesA run_id returned by a research tool, such as person-<id> or set-<id>, up to 200 characters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

B3.3/5.0
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 safety profile is covered by structured data. The description earns credit by adding consequences the annotations cannot convey: completed work may still be charged, including people admitted to a search before it stopped. It stops short of 5 because it does not say whether cancellation is immediate or reversible, nor whether partial results remain retrievable.

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

Conciseness4/5

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

Two short sentences with the action first and the cost warning second; nothing is padded. The opening clause 'when the user asks to cancel' is mildly redundant with the tool name, keeping it just below a 5.

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

Completeness3/5

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

With one required parameter, a full schema description, and no output schema, the definition covers the essential billing risk. It is still thin for a destructive, open-world operation: an agent gets no signal about what happens on an invalid or already-finished run_id, nor what the call returns.

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?

There is a single parameter with 100% schema description coverage, so the schema already explains that run_id comes from a research tool with patterns like person-<id> or set-<id>. The description adds no further meaning about the identifier, which is the expected baseline when the schema does the work.

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

Purpose3/5

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

The description says 'Stop a research run', which is a concrete verb and resource, so an agent can tell it apart from get_research_status in principle. However, the qualifier 'when the user asks to cancel' largely restates the tool name rather than scoping what a run is or what stopping it does, so it stops short of the differentiation a 4 or 5 requires.

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

Usage Guidelines3/5

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

The phrase 'when the user asks to cancel' gives an implied trigger condition, which is more than nothing. It does not state when cancellation should be avoided (e.g. a run that is already finishing) or point to any alternative such as checking status first via get_research_status.

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