Runs a specific task within a supervised workflow and returns evidence, enabling primary agents to delegate coding work to background subagents with approval checks.
Execute a specific task in a run through the supervised workflow and return evidence.
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes | ||
| command | No | ||
| task_id | Yes |
Changes observed during successful MCP inspections.
v1.1.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full burden. It implies side effects (executing a command inside a run) and mentions returning "evidence," but says nothing about what the supervision entails, whether an approval gate blocks execution, whether the command is destructive, whether a failure leaves the run in a partial state, or what the evidence looks like.
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?
A single declarative sentence with no filler, and the key action is front-loaded. It is efficient, but its brevity is achieved by omitting rather than by compressing useful 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?
For an execution tool with no annotations, no output schema, and 0% parameter coverage, this description is far too thin. The one piece of output information it does offer ("return evidence") is likely covered by the sibling get_task_evidence, and the mechanics of supervised execution — the thing most likely to trip an agent up — are left entirely unexplained.
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?
Schema description coverage is 0% across all three parameters. The description only obliquely references run_id and task_id via the words "run" and "task," and it says nothing at all about the optional "command" array — its format, whether it overrides the task definition, or what happens when it is null.
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 gives a specific verb ("Execute") and resource ("a specific task in a run"), so the agent knows the unit of work is a task rather than a whole run. However, it never names the sibling it differs from (execute_run, submit_goal), so the distinction has to be inferred from the wording alone.
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 phrase "through the supervised workflow" hints that there is a gated process, but the description never states when to use this tool versus execute_run, submit_goal, or get_task_evidence. There are no prerequisites, no exclusions, and no note about whether the task must already exist in the run.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.