Stops, resumes, or deletes a surrogate build: finished points are kept, stopped or interrupted runs can resume, and deletion requires confirmation with the study ID.
Stop a build (finished points are kept), resume a stopped or interrupted one, or delete it (confirm = study_id).
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | ||
| confirm | No | ||
| language | No | ja | |
| study_id | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds real behavior beyond the annotations: it discloses that stopping preserves finished points, that resume works on both stopped and interrupted states, and that delete is gated by a confirmation argument. It stops short of saying what delete actually destroys (all progress and results?) or whether stop can be reversed, which the destructiveHint=true annotation makes relevant.
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 front-loaded sentence with parenthetical clarifications that each earn their place; no filler, and the most dangerous action's precondition is stated inline.
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 destructive, non-idempotent mutation with no output schema and zero schema documentation, this is only adequate. Key gaps remain: the irreversible consequences of delete, what the tool returns for each action, and the meaning of the language parameter.
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%, so the description must carry the parameter burden. It explains the action enum values and the non-obvious confirm = study_id convention for delete, but leaves the language parameter (default 'ja') completely unexplained and says nothing about study_id's scope.
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 three specific verbs (stop, resume, delete) applied to an in-progress build, so an agent can tell this is a build lifecycle control tool rather than a query or creation tool. It doesn't explicitly contrast itself with the closely related build_surrogate or surrogate_status siblings, keeping it short of a 5.
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?
Per-action conditions are given well: stop is for halting while keeping finished points, resume applies to a 'stopped or interrupted' build, and delete requires confirm = study_id. What's missing is routing guidance against siblings — nothing says to check surrogate_status first or that build_surrogate is the way to start a new one rather than resuming.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
This server cannot be deployed