Discards the kept result of a finished background run so it is no longer retained; started runs continue to completion.
[read-only] [runtime] Removes the kept answer of one of your finished background runs. Works on a finished run; a started run runs to its end. Runs outside batch mode.
| Name | Required | Description | Default |
|---|---|---|---|
| run_handle | Yes | The run_handle a run started with background=true answered. |
Changes observed during successful MCP inspections.
v20.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full burden, yet it leads with a '[read-only]' tag while describing an operation that removes data — an internally inconsistent safety signal for an agent deciding whether to invoke it. It also never says whether the removal is recoverable or whether the run record itself survives, both critical for a discard operation.
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?
Three short sentences with no filler, and the core action is front-loaded ahead of the edge-case conditions. The bracketed tag prefix adds noise and the self-contradiction costs a point.
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?
There is no output schema and no annotations, so the description is the only source for outcomes: it explains the running-run and batch-mode cases but omits what the tool returns, whether the run persists after the answer is discarded, and whether the action is reversible. Adequate but with meaningful gaps for a destructive tool.
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 single parameter is fully documented in the schema (100% coverage), including how a run_handle is obtained ('answered' by a run started with background=true'). The description adds no constraints such as handle validity or staleness, so the schema does the work and baseline 3 applies.
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?
States a specific verb and resource: removing the kept answer of a finished background run. This distinguishes it from read-only siblings like GetBackgroundRun and ListBackgroundRuns, which surface the same objects. The phrase 'kept answer' is slightly opaque about exactly what artifact is deleted, keeping it from a 5.
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?
'Works on a finished run; a started run runs to its end' gives a clear precondition and edge-case behavior, and 'Runs outside batch mode' is an explicit exclusion. It never names an alternative sibling or explains what to use instead if the run is still active, so it stops short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.