Retrieve counts of guardrail decisions—ok, blocked, redacted, alerted, and errored—across LLM interactions, optionally filtered to a single agent.
Guardrail-decision counts (ok/blocked/redacted/alerted/errored) across LLM interactions, optionally scoped to one agent.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | No |
Changes observed during successful MCP inspections.
v0.2.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so the description carries the full burden. It usefully discloses what is computed (per-category decision counts) rather than raw records, but says nothing about time range, default scope, aggregation window, or whether it is all-time data.
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?
One compact sentence with the resource and metric front-loaded and the optional scope trailing. Every element earns its place; nothing is padded.
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?
With no output schema, the description does the work of listing returned categories, which is the key missing piece. However it omits the aggregation scope (time window, session vs interaction grouping), leaving the agent unsure what set of data is being counted.
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?
The single agent_id parameter has 0% schema description coverage, so the description must compensate. 'Optionally scoped to one agent' does convey its meaning and optional nature, but adds no format, ID-type, or default behavior detail.
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 (counts) and resource (guardrail decisions across LLM interactions) and enumerates the counted categories (ok/blocked/redacted/alerted/errored). This separates it from list_llm_interactions and get_guardrail_outcomes without naming them explicitly.
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 only usage signal is 'optionally scoped to one agent', which is a filter hint rather than guidance. It never says when to reach for this aggregate versus get_guardrail_outcomes or get_guardrail_categories, nor any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.