cancel_workflowCancel an in-progress workflow. All queued and dispatched steps are marked CANCELLED. Completed steps are not reversed. You are only billed for steps that completed before cancellation.
| Name | Required | Description | Default |
|---|---|---|---|
| workflow_id | Yes | Workflow ID to cancel. |
| Name | Required | Description | Default |
|---|---|---|---|
| status | No | ||
| cancelled | Yes | ||
| workflow_id | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Even with annotations declaring readOnlyHint=false and idempotentHint=true, the description adds critical behavioral details: queued/dispatched steps are marked CANCELLED, completed steps are not reversed, and billing only applies to completed steps. This goes beyond the annotations and gives agents clear expectations about side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, each contributing essential information: what the tool does, the effect on steps, and the billing implication. It is front-loaded with the action and contains no redundant or filler content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple (one parameter, output schema present, annotations provided), and the description covers the main behavioral facets including billing and non-reversal of completed steps. It does not explicitly address the behavior when the workflow is already completed or not in-progress, but the idempotentHint annotation mitigates this concern, making the description nearly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already provides 100% coverage for the single required parameter with the description 'Workflow ID to cancel.' The tool description does not add additional parameter-level detail, which is acceptable since the schema is sufficient. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with 'Cancel an in-progress workflow,' which uses a specific verb and resource, clearly distinguishing this from sibling tools like submit_workflow or get_workflow_status. It also describes the effect on queued/dispatched steps, making the tool's purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use this tool (when you need to stop an in-progress workflow) but does not explicitly state alternatives or when not to use it. The billing note and step-marking behavior provide context for deciding if cancellation is appropriate, but no direct sibling comparisons are made.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each operation is split into clear source-specific variants (URL, uploaded file, inline content), and the descriptions go to great lengths to distinguish them. The only mild ambiguities are generic-sounding names like transcode_video versus transcode_from_url, and the similar get_job_status/get_workflow_status pair, but there is no true functional overlap.
Most tools follow an imperative verb_noun pattern and use recurring suffixes like _from_url, _content, and _file, which creates a readable family structure. The pattern breaks slightly with uploaded-media variants named conform_media, transcode_video, and transcribe_media instead of a consistent _file or _uploaded suffix, and transcode_content is referenced in a description but missing from the actual tool list.
17 tools is slightly above the ideal 3-15 range, but the server covers several related subdomains: document conversion, media transcode/transcribe/conform, job/workflow lifecycle, and wallet/billing. Given the need for URL, uploaded, and inline variants across multiple media types, the overall count is reasonable.
Core workflows are well covered: uploading, job submission, polling, and retrieving outputs all exist, and conversion has content/file/URL routes. However, get_upload_url explicitly tells agents to use transcode_content for inline media, but that tool does not exist, and there is no inline transcribe counterpart to convert_content, leaving a notable gap for sandboxed inline media jobs.