Create or update a custom resource action in VCF Automation by submitting its definition, criteria, runnable item, and form configuration through the Form Service API.
Create resource action. POST /form-service/api/custom/resource-actions
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | The resource action | |
| generateUnvalidatableExternalValuesSchema | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly=false, idempotent=false, openWorld=true and destructive=false, so the safety profile is present in structured fields. The description adds only the HTTP verb/path and says nothing about required permissions, validation behavior, upsert semantics, or side effects of creating/updating a resource action.
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?
It is two lines and front-loaded, but the second line merely restates the endpoint and the first is too terse for a complex nested-body mutation. The brevity leaves out necessary context rather than trimming redundancy.
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 mutation tool with a large nested object, 50% schema coverage, and no output schema, the description is far from complete. It does not explain what constitutes a valid resource action or what the response will contain, leaving the agent to infer from the schema alone.
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?
Two parameters exist and schema description coverage is 50%, with top-level body fields such as id, name, orgId, status, criteria, and runnableItem largely undocumented by the description. The description gives no meaning, format, required-field guidance, or interaction for the nested body object or the generateUnvalidatableExternalValuesSchema flag.
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 ('Create') and resource ('resource action'), and confirms the POST endpoint. This distinguishes it from delete/get siblings by name, but it does not explain the 'or_update' part of the tool name or when an existing action is updated rather than created.
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?
Provides no when-to-use guidance, prerequisites, or alternatives such as form_get_resource_action or form_delete_resource_action. The only context is the endpoint path, which does not help an agent choose this tool over other form-service mutations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.