Execute subprocesses with vault-stored secrets injected as environment variables, then scrub stdout and stderr for raw, Base64, and URL-encoded leaks.
Execute a subprocess with {{vault:sec_}} or {{vault:lease_}} handles injected into environment variables, scrubbing stdout and stderr for raw, Base64, and URL-encoded secret leaks.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | ||
| env | Yes | ||
| args | No | ||
| command | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose one genuinely valuable trait: stdout/stderr are scrubbed for raw, Base64, and URL-encoded secret leaks. It omits other consequential behavior for a subprocess executor — permission requirements, sandboxing, exit-code/timeout handling, and whether the command runs with the caller's privileges.
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 dense sentence that front-loads the action and immediately follows with the injection mechanism and the scrubbing guarantee. Every clause carries information; only the URL/Base64 enumeration feels slightly list-heavy.
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 a security-sensitive subprocess executor with no annotations, no output schema, and 0% parameter documentation, the description covers the two most distinctive behaviors (handle injection and leak scrubbing) but leaves permissions, isolation, and return/exit behavior unaddressed.
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 4 parameters, so the description must compensate, and it largely does not. It clarifies the semantics of 'env' (values may contain {{vault:sec_<ulid>}} / {{vault:lease_<ulid>}} handles), but says nothing about 'command', 'args', or 'cwd'.
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 ('Execute a subprocess') and adds the distinctive mechanism (vault handle injection into env vars). It does not, however, explicitly differentiate itself from the close sibling vault_inject_env or vault_http_proxy, so an agent must infer the distinction.
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 handle syntax hints at when the tool is applicable (you hold sec_/lease_ handles), but there is no explicit when-to-use, when-not-to-use, or naming of alternatives such as vault_inject_env. An agent gets no routing guidance between the sibling execution/injection tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.