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 |
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.
Tools are largely distinguishable by their action and input source (content/file/url), but the multiple convert_* and transcode/transcribe variants overlap in purpose, and get_job_status vs get_workflow_status could cause confusion. Descriptions are thorough enough to guide selection, but the boundaries between similar actions are not always crisp.
All names use snake_case with a verb-noun pattern (get_, convert_, transcode_, transcribe_, submit_, cancel_), which is consistent. However, the variant naming is not perfectly parallel: convert_content/file/from_url use a source suffix, whereas transcode_video vs transcode_from_url and transcribe_media vs transcribe_from_url mix output type and source, creating minor inconsistency.
At 15 tools, the server is at the upper end of a well-scoped set. Each tool supports a distinct input/output route or workflow function, but the count is slightly heavy due to multiple variants of similar operations. It remains appropriate for the breadth of conversion, transcoding, transcription, workflow, and wallet features.
The core job lifecycle (submit, poll, retrieve output) is well covered, and workflows have submit/status/cancel. However, get_upload_url references a transcode_content tool that does not exist in the toolset, and there is no way to cancel a single job (only full workflows). This leaves gaps for inline media transcoding in sandboxed environments and granular job control.