List per-agent guardrails and filter by status or recipe_id to monitor and manage agent behavior rules.
List per-agent guardrails. Filter by status or recipe_id.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| cursor | No | opaque pagination token from previous response next_cursor; pass through unchanged | |
| status | No | ||
| recipe_id | No |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint and openWorldHint annotations already disclose the safety profile, so the description does not need to restate that. The description adds the per-agent scoping and filter capabilities, but it does not discuss pagination behavior, result ordering, or the meaning of openWorldHint. With annotations present this is adequate but not richly transparent.
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?
The description is a single, efficient sentence that says what the tool does and what filters are available. There is no filler or repetition; it is front-loaded with the core action and resource.
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 list tool, the description captures the core purpose and filters, and the schema provides some parameter structure. However, without an output schema or any note about pagination, limit behavior, or what fields are present in the response, an agent may lack full context for interpreting results. Still, the tool is simple enough that this is a moderate gap.
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 only 25% (only cursor is documented). The description mentions 'status' and 'recipe_id' as filters, adding some conceptual value, but it does not explain 'limit' or clarify pagination, and 'recipe_id' itself is left undescribed in both schema and description. This only partially compensates for the low schema coverage.
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 uses a specific verb and resource: 'List per-agent guardrails.' It clearly distinguishes this from the sibling guardrail_get, guardrail_create, guardrail_update, and guardrail_promote tools by focusing on listing with optional filters. The filter mention ('by status or recipe_id') further narrows the tool's purpose.
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 implies the tool should be used to enumerate guardrails, optionally filtered, but it does not explicitly state when to choose this over guardrail_get or other guardrail-related tools. There is no mention of exclusions or alternative tools, though the overall list semantics make the use case reasonably inferable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.