Skip to main content
Glama
GethosTheWalrus

Temporal MCP Server

batch_cancel

Cancel multiple Temporal workflows matching a query, processing cancellations concurrently. Set limit and concurrency to control how many workflows are cancelled in parallel.

Instructions

Cancel multiple workflows matching a query with concurrent processing for speed. Use 'concurrency' to control parallel operations (default: 50).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of workflows to cancel (default: 100)
queryYesQuery to select workflows to cancel
namespaceNoTemporal namespace for this operation; omit to use the server default
concurrencyNoNumber of workflows to cancel concurrently for faster processing (default: 50, max recommended: 100)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.10.1
    • addedInput schema / properties / namespace
      Added value: +{
      +  "description": "Temporal namespace for this operation; omit to use the server default",
      +  "enum": [
      +    "default"
      +  ],
      +  "minLength": 1,
      +  "type": "string"
      +}
  2. Addedv1.9.0
  3. Removedv1.5.0
  4. First observedv1.3.0

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations, the description carries the full burden and falls short. It never states that cancelling is a graceful/irreversible destructive operation, whether the operation is idempotent, what happens to workflows that don't match, or how failures and results are reported for a batch.

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, front-loaded with the action and scope; nothing is padded. The second sentence is partially redundant with the schema's concurrency description, costing a point.

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

Completeness2/5

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

For an unannotated bulk destructive operation with no output schema, the definition omits too much: no return/result reporting, no partial-failure behavior, no distinction from batch_terminate, and no warning that cancellation is effectively irreversible.

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 description coverage is 100%, so all four parameters (limit, query, namespace, concurrency) are already documented, including the concurrency default of 50. The description merely restates the concurrency semantics, adding no meaning beyond the schema, which is the expected baseline.

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 and resource ('Cancel multiple workflows matching a query'), clearly scoped to bulk operations versus the single-workflow cancel_workflow sibling. It does not, however, distinguish itself from the adjacent batch_terminate / batch_cancel_activities siblings, so the agent must infer which is appropriate.

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

Usage Guidelines2/5

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

No when-to-use guidance is given: nothing says when to pick batch_cancel over cancel_workflow or batch_terminate, and no prerequisites or cautions are stated. The only directive is how to tune concurrency, which is execution detail rather than selection guidance.

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