Apply an atomic batch of typed graph edits to a RunningHub workflow using compare-and-swap, so failed batches create no new revision.
Apply an atomic typed graph edit batch using compare-and-swap; failed batches create no revision.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | Yes | ||
| operations | Yes | ||
| workflow_id | Yes | ||
| base_revision_id | 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 must carry the full behavioral burden, and it does disclose two important traits: batch atomicity and all-or-nothing failure semantics ('failed batches create no revision'), plus the CAS precondition implied by 'compare-and-swap'. However, it omits what happens on a revision conflict, permission requirements, and the meaning of the required 'reason' field.
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?
A single front-loaded sentence that conveys the action, the atomicity guarantee, and the failure behavior with zero filler. Nothing redundant and nothing buried.
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 high-complexity mutation tool with ten operation variants, no annotations, no output schema, and 0% schema coverage, the description is far too thin. It never explains the CAS precondition that base_revision_id encodes, the role of 'reason', or the semantics of the operation batch it accepts.
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% across 4 required parameters and a deeply nested union of ten operation types, so the description is the only source of meaning. It obliquely signals that base_revision_id drives compare-and-swap, but adds nothing about workflow_id, reason, or the operations structure, leaving most parameters undocumented in both schema and description.
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 specific verb+resource pair ('Apply an atomic typed graph edit batch') and names the concurrency mechanism ('compare-and-swap'), so an agent can tell this mutates a workflow graph rather than reading, validating, or creating one. It stops short of explicitly distinguishing itself from close siblings like rh_create_workflow or rh_validate_workflow.
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?
No when-to-use, when-not-to-use, or prerequisite guidance is given. An agent gets no signal on whether to call rh_validate_workflow or rh_get_workflow first, or when to prefer this over rh_create_workflow. Only the failure trait ('failed batches create no revision') hints at context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.