Retrieve the Docker Compose YAML Purgatory deployed into a named sandbox, with secrets masked. Use it to inspect the starter stack running in that sandbox.
The starter stack Purgatory deployed into the sandbox (compose YAML), secrets masked HTTP GET /sandboxes/{name}/compose
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes |
Changes observed during successful MCP inspections.
v0.7.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already establishes this is a safe read. The description adds meaningful context by disclosing that secrets are masked in the returned compose YAML, which is beyond what annotations provide, but it says nothing about pagination, auth, or response structure.
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?
It is short with no filler, but the structure is poor: the leading noun fragment is fragmented and runs into the unpunctuated HTTP endpoint, harming front-loading and readability.
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 single-parameter read tool with readOnlyHint and no output schema, the essentials are mostly covered by name, endpoint, and the secrets-masking note. It stops short of describing the returned content or any conditions under which the stack might be unavailable.
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 0%, so the description must carry the single 'name' parameter. The endpoint line 'GET /sandboxes/{name}/compose' does imply that 'name' is the sandbox identifier, partially compensating, but no format or constraints are clarified.
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 identifies the resource (the starter stack's compose YAML) and the endpoint, so an agent can infer this returns a compose file. However, it is phrased as a noun fragment without a clear verb, and the reference to 'Purgatory' is unexplained, making the exact purpose only implied rather than stated.
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 guidance on when to use this tool versus siblings like get_sandbox, read_sandbox_file, or sandbox_summary, and no prerequisites or exclusions are given. The agent must infer the use case entirely from the name and the HTTP line.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.