Табуля

files_run_cancel

Idempotent

Cancels a previously started files_run task by its task_id (only the task's owner can cancel). Marks the task so the worker won't pick it up; a task that is already running may still finish. Returns whether it was cancelled. Signature: files_run_cancel(task_id, file_uuid?).

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": {
      "task_id": "<task_id>"
    },
    "name": "files_run_cancel"
  }
}

Input Schema

Name	Required	Description	Default
`task_id`	Yes	The task id returned by files_run.
`file_uuid`	No	The file the task was started for. When given, a task belonging to another file is reported as not found. Required when connected with a space API token.

Output Schema

Name	Required	Description	Default
`fileUuid`	Yes
`taskUuid`	Yes
`cancelled`	Yes
`previousStatus`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 31, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing soft-cancel semantics: it only marks the task so the worker won't pick it up, and an already-running task may still finish. This reconciles the non-obvious combination of a state-changing call with destructiveHint=false and confirms the boolean result lets the caller detect a no-op.

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?

Front-loaded with the core effect and the ownership constraint, with no filler in the prose. The appended 'Signature: files_run_cancel(task_id, file_uuid?)' line is pure redundancy against the schema and is the one thing that doesn't earn its place.

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

Completeness5/5

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

For a two-parameter mutation with an output schema, everything an agent needs is covered: ownership gate, partial-cancel semantics, and the fact that a boolean is returned. The conditional file_uuid token requirement is reinforced rather than left solely to the schema.

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%: both task_id and the conditional file_uuid (required under a space API token) are already fully documented in the schema. The description restates the same facts and the trailing signature line adds no new meaning, so it neither compensates nor misleads — baseline applies.

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

Purpose5/5

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

Uses a specific verb (cancels) plus the exact resource and the identifier that scopes it ('a previously started files_run task by its task_id'). The pairing with files_run / files_run_status is implicitly clear from the name and 'previously started' phrasing, so an agent can distinguish this as the termination operation.

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?

States the precondition that the task must be previously started and that only the owner can cancel, which tells the agent when the call will succeed. It doesn't name alternatives such as files_run_status for polling rather than cancelling, so routing guidance is present but not exhaustive.

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

All Табуля tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?