compile_report

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full responsibility for disclosing side effects and behaviors. It goes beyond a simple 'compile' statement by explicitly mentioning optional evaluation of SLOs, SignalPilot, and Reveal, plus the knee-results edge-case behavior. It also states what is returned ('verdict, written paths, and the report dict'), implying file-writing side effects.

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 four sentences, each delivering distinct value: core purpose, sequencing, special-case guidance, and return summary. No filler or redundant phrasing; it is front-loaded with the most essential information and remains compact.

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 moderate complexity (5 params, output schema present), the description covers typical usage, a special discovery-run scenario, and return value. It does not elaborate on parameter relationships (e.g., namespace), but the existing schema and output schema reduce the need for that detail. Overall, it provides sufficient context for an agent to select and invoke the 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?

Schema description coverage is 0%, so the description must compensate. It explicitly explains the non-obvious use_knee_results parameter and hints at slo_path and use_reveal through 'Optionally evaluates SLOs ... and Reveal.' However, namespace and the exact relationship between slo_path and SLO evaluation are left implicit. It adds meaning but does not fully define every parameter.

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 opens with 'Compile Markdown/HTML/JSON artifacts with a verdict-led summary,' which clearly specifies the action (compile), the resources (artifacts), and the purpose. It distinguishes itself from sibling tools like analyze_results and evaluate_slo by focusing on report generation rather than analysis or evaluation.

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?

'Use after analyze/evaluate' explicitly indicates the correct sequencing and positions the tool as a downstream step. The additional instruction for discovery runs—'set use_knee_results=true to analyze/SLO the knee step JTL when a knee exists'—provides scenario-specific guidance that helps the agent decide when to adjust the default behavior.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.