Remove one file from a Config, or the whole Config and its mounts. Staged. This call asks no human.
| Name | Required | Description | Default |
|---|---|---|---|
| file | No | One file to remove. Omit to remove the whole Config and unmount it everywhere. | |
| config | Yes | ||
| project | No | Project name. | |
| environment | No | Environment name, e.g. staging. | |
| expect_revision | No | Writes only if the place is still at this revision. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
'Staged' and 'This call asks no human' add real context beyond the annotations: the removal is queued rather than immediately applied, and no approval gate exists, which also explains why destructiveHint is false despite a delete-shaped tool. What is not disclosed is the effect on workloads currently mounted to the Config, which matters for a full-Config removal.
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 two removal scopes, then the staging and approval facts. No sentence is filler.
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 five-parameter removal tool with no output schema, the definition covers the modes, staging semantics, and the lack of human approval. It leaves open how a staged removal is committed and what happens to running mounts on full-Config removal, which is a meaningful gap for a destructive operation.
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 80%, so the schema already documents file, project, environment, and expect_revision. The description corroborates the file-omission behavior but adds no format, constraint, or revision-conflict detail beyond the schema, which is the expected baseline here.
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 names a specific verb (Remove) and both scopes it operates on: a single file inside a Config, or the entire Config plus its mounts. That is enough to separate it from config_write and config_rename without opening a schema. It stops short of a 5 because no sibling is named explicitly.
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 dual mode is stated (file vs. whole Config), and the schema reinforces that omitting 'file' removes everything. However, there is no guidance on when to prefer this over alternatives such as discard, config_write, or a subsequent deploy to apply the staged change, so usage is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
