Runtime Correlation

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

Annotations indicate readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds behavioral context: it distinguishes between output with and without an audit log, and explains the risk-amplified findings. It does not contradict annotations and provides useful behavioral details beyond what annotations alone convey.

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 front-loaded with the main purpose and uses bullet points for the return value. It is clear and each sentence adds value, though it could be slightly more concise.

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 complexity, the description covers the main purpose, required inputs, alternative behavior (without audit log), and output format. It does not reiterate the output schema since one exists, making it sufficiently complete for an agent to understand when and how to 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 100% with detailed per-parameter descriptions. The tool description adds further context, such as the OTel trace being used for ML API call provenance, enriching the meaning beyond the schema.

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 clearly states it cross-references vulnerability scan results with proxy runtime audit logs to identify which vulnerable tools were actually called. It uses specific verbs like 'cross-reference', 'identifies', and 'distinguishing confirmed attack surface from theoretical risk', which differentiates it from siblings like ai_inventory_scan or audit_query.

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 explicitly states the requirement for a proxy audit log and explains what happens without it ('returns scan results only'). It also mentions the OTel trace as an optional input. While it does not explicitly list alternatives or when not to use, it provides clear context on prerequisites and fallback behavior.

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