List built-in operational-check recipes to browse available controls and select one to promote into a guardrail.
List built-in operational-check recipes (registry of controls). Promote one into a guardrail via invariance_guardrail_create.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| cursor | No | opaque pagination token from previous response next_cursor; pass through unchanged |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, covering the safety profile. The description adds the 'built-in' and 'registry of controls' context, but it does not disclose behavioral details such as pagination behavior or output shape, which is acceptable given the annotations carry the main burden.
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?
Two sentences with zero filler. The core listing purpose is front-loaded, and the promotion path is given in a single clear follow-up sentence.
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 simple read-only list operation with no required parameterscing and a cursor schema description, this is mostly complete. It tells the agent what the tool lists and what to do next, though it omits any hint of return value fields, which would be more important given there is no output schema.
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 50%: cursor is described in the schema, but limit is not, and the tool description mentions neither parameter. Since the description adds no parameter-level meaning and does not compensate for the undocumented limit, this falls short despite the parameter name being somewhat self-explanatory.
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 a specific verb ('List'), resource ('built-in operational-check recipes'), and clarifies scope with 'registry of controls'. It also distinguishes the tool by pointing to the promotion workflow via invariance_guardrail_create, separating it from recipe-specific tools like get/update.
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?
The description makes the primary use clear and explicitly directs the agent to invariance_guardrail_create for the follow-up action. However, it does not state when not to use this tool or contrast it with invariance_recipe_get or invariance_guardrail_list, so exclusions are missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.