Execute shell commands inside an app's running container to inspect or debug it; returns exit code, stdout, and stderr within 60 seconds.
Execute a command inside an app's running container. Timeout is 60 seconds. Returns exit code, stdout, and stderr.
| Name | Required | Description | Default |
|---|---|---|---|
| app_id | Yes | App ID (UUID) | |
| command | Yes | Shell command to execute in the container | |
| working_dir | No | Working directory inside the container |
Changes observed during successful MCP inspections.
v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, non-idempotent, openWorld, so the safety profile is covered. The description adds real value beyond that: the 60-second timeout and the exact return contract (exit code, stdout, stderr), which an agent needs to interpret results.
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, front-loaded with the action, then timeout and return shape. Every sentence carries information and nothing is wasted.
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 three-parameter execution tool with no output schema, the description covers purpose, timeout constraint, and return values. It could note that the app must be running or the execution context, but is otherwise sufficient to call correctly.
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 100%, so all three parameters are documented in the schema itself. The description adds no parameter-level detail, so the baseline of 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: execute a command inside an app's running container. This is unambiguously distinct from every sibling (logs, restart_service, deploy, etc.), and an agent can tell what it does without opening the schema.
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?
Usage is only implied by the nature of the operation; there is no explicit when-to-use, when-not-to-use, or named alternative (e.g. get_logs for read-only inspection). An agent can infer context but gets no routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.