Removes an experiment from splithub.config.ts and archives it in SplitHub Cloud when connected, without code changes; returns references still in the code. Use ship to also clean code.
Remove an experiment from splithub.config.ts (and archive it in the cloud when connected) without touching the code. Prefer splithub_ship, which also cleans the code. Returns refs still in the code.
| Name | Required | Description | Default |
|---|---|---|---|
| experiment | 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 discloses meaningful traits: config-file removal, optional cloud archival when connected, that source code is left untouched, and the return payload ('refs still in the code'). It does not say whether removal is reversible or what happens if the experiment does not exist.
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 and file affected, then the preferred alternative, then the return value. Every sentence adds information with no 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 single-parameter mutation with no annotations and no output schema, the description covers behavior and return value well, but leaves the identifier format and failure/irreversibility semantics unexplained. Adequate, with clear remaining gaps.
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% and the description never clarifies whether 'experiment' is a slug, display name, or ID, nor any format constraints. Only the generic implication that the argument identifies an experiment is conveyed.
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 concrete verb and resource ('Remove an experiment from splithub.config.ts'), plus the cloud-archival side effect, and explicitly contrasts with splithub_ship which also cleans code. An agent can distinguish it from all sibling tools 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?
'Prefer splithub_ship, which also cleans the code' gives an explicit alternative and the condition that selects it. It lacks an explicit 'when not to use' or prerequisite statement, but the routing guidance is clear enough to act on.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.