research-workflow-studio

Overview Schema Source Related Servers Discussions Admin

rws_operation_propose

Idempotent

Propose reviewed Git and task operations for approval without execution; read-only inspections can run via a local runner, while workspace mutations need exact human approval.

Instructions

Propose a literal reviewed Git/task operation. No execution occurs. Read-only inspections may be claimed by an explicit local runner; workspace/process mutations need exact human approval.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "requestId": "<requestId>",
      "projectId": "<projectId>",
      "expectedRevision": "<expectedRevision>",
      "record": "<record>"
    },
    "name": "rws_operation_propose"
  }
}

Input Schema

Name	Required	Description	Default
`record`	Yes
`projectId`	Yes
`requestId`	Yes
`expectedRevision`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.4.2Oct 30, 2026

TDQS

B3.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds the crucial nuance that the tool records a proposal without executing anything, and that mutations require exact human approval. It does not say what is persisted, what is returned (e.g., an operation id for the approval step), or how expectedRevision conflicts behave.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and its no-execution guarantee; every sentence carries signal. The clause about an "explicit local runner" is slightly opaque but not padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with an 11-variant polymorphic record schema, no output schema, and zero parameter descriptions, the description covers purpose and approval policy but omits the operation kinds available, the concurrency token semantics, and what a successful call returns. An agent could not construct a valid record from the description alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across a very large schema, including an 11-variant oneOf record union, yet the description never mentions requestId, projectId, expectedRevision, or the record kinds. Nothing explains that expectedRevision is an optimistic-concurrency token or that requestId is an idempotency key, so the description fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Propose a literal reviewed Git/task operation") and immediately bounds scope with "No execution occurs." An agent can tell this apart from rws_operation_approve / rws_operation_dismiss by the verb, though those siblings are never named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than routed: read-only inspections can be claimed by a local runner, mutations need human approval. The description never names the approval tool or states the follow-up step, so the agent must infer that proposing is the first half of a propose→approve workflow.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.