Purge transient spool chunks, staging files, and open multiplexed sockets across Appliance and Bastion; reuse an optional transaction ID to retrieve the operation without replaying ambiguous work.
Purge transient spool chunks, staging files, and open multiplexed sockets across Appliance and Bastion.
| Name | Required | Description | Default |
|---|---|---|---|
| tx_id | No | Optional stable transaction id. Reuse retrieves the original operation and never replays ambiguous work. |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full behavioral burden. It does disclose exactly which artifacts are removed (spool chunks, staging files, multiplexed sockets), which is the single most important fact for a purge operation and hints at low blast radius via 'transient'. It does not state whether deletion is irreversible, whether in-flight transactions on those sockets are aborted, or what permissions are required.
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?
One sentence, front-loaded with the verb and the affected artifacts, with no filler or redundancy. Every clause names a distinct target class.
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?
With one optional parameter, no output schema, and no annotations, the definition is close to sufficient: the agent knows what is destroyed and where. The remaining gap is operational safety — irreversibility and effect on live sockets/transactions — which matters for a purge tool but is partially mitigated by 'transient'.
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 coverage is 100% and the single optional tx_id parameter is documented thoroughly in the schema, including its idempotency semantics. The description adds nothing about tx_id, so the schema does all the work; 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?
The description uses a specific verb ('Purge') and enumerates concrete resources: transient spool chunks, staging files, and open multiplexed sockets, scoped across Appliance and Bastion. That is far more informative than the bare name. It does not, however, differentiate itself from adjacent siblings such as enclave_heal or enclave_doctor, which likely also remediate state.
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?
There is no statement of when to invoke this versus enclave_heal, enclave_doctor, or enclave_transaction, and no preconditions or exclusions. The word 'transient' weakly implies it is safe cleanup, but the agent is left to infer the trigger conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.