Compare two agent traces to detect regressions. Returns score delta, cost delta, added/removed tools, new/resolved issue types.
| Name | Required | Description | Default |
|---|---|---|---|
| trace_a | Yes | Baseline (previous) trace | |
| trace_b | Yes | New trace to compare against baseline | |
| budget_usd | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It discloses key return information (score delta, cost delta, added/removed tools, issue type changes), which is useful. However, it does not mention whether the operation is read-only, any side effects, or limitations regarding input size or trace format.
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, front-loaded sentence that efficiently lists the return values without unnecessary words. Every phrase earns its place, and the list format is easy to scan.
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?
Given the tool's simplicity (2 required params, no output schema, no nested objects), the description covers the core purpose and return contents. However, the budget_usd parameter is unexplained, and no guidance is given on how this tool fits with sibling tools, leaving moderate gaps in completeness.
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 schema provides descriptions for trace_a and trace_b, but the description adds little beyond that. More importantly, budget_usd has no schema description and the tool description does not clarify its meaning or relation to the 'cost delta' output, leaving a significant gap.
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 'Compare' with a clear resource 'two agent traces' and states the purpose 'detect regressions'. This distinguishes it from siblings that likely operate on a single trace, such as audit_trace and quick_verdict.
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 use when comparing a baseline and new trace to detect regressions, providing clear context. However, it does not explicitly state when not to use this tool or mention alternative tools by name, so it lacks explicit exclusions or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct need: full audit, trace comparison, and fast CI verdict. There is no overlap in purpose or output.
Three tools use snake_case and are clear, but audit_trace and diff_traces follow verb_noun while quick_verdict is adjective_noun, breaking the pattern slightly.
Three tools are well-scoped for a focused auditor server. The count is appropriate and each tool serves a clear, non-redundant role.
The toolset covers deep audit, regression comparison, and quick gating. Minor gap: no explicit tool for retrieving raw trace data, but it's likely out of scope.