Audit every human approval, denial, and edit in agent traces: see who decided, the rationale, and why an action was allowed or blocked.
Human-in-the-loop audit: every approval/denial/edit, who decided, and the rationale.
Use when asked 'why did the agent get to do X?' or 'what was denied?'.
| Name | Required | Description | Default |
|---|---|---|---|
| trace_id | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.6.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the content and the human-in-the-loop nature of the log, but never states that it is read-only, how far back the log goes, whether results are paginated, or whether it requires a trace_id. Meaningful behavioral traits beyond the payload are left unstated.
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 short sentences with zero filler: the first states what the log contains, the second states when to reach for it. Front-loaded and appropriately sized for a single-parameter read tool.
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?
An output schema exists, so return values need not be described here. However, with no annotations and an undocumented optional trace_id, the description leaves the agent unsure whether a call returns the whole log or requires scoping, which is a real gap for an audit tool.
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?
There is 1 parameter (trace_id) with 0% schema description coverage, and the description never mentions it. The phrase 'every approval/denial/edit' actually implies a full log, giving no hint that passing trace_id narrows scope or that omitting it returns everything.
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 resource (approval/denial/edit audit log) and enumerates its contents (decision, decider, rationale), so the agent knows exactly what is returned. It does not explicitly contrast itself with near-siblings like security_audit or failure_report, so it falls short of a 5.
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?
It gives concrete trigger phrasings ('why did the agent get to do X?', 'what was denied?'), which is clear when-to-use guidance. It stops short of naming an alternative tool or stating when NOT to use it, so no exclusion guidance is present.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.