audit_scan

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

Annotations declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, and the description is consistent with them while adding real context: the scan relies on cached intelligence (no network call) and persists an evidence report as a side effect. It does not say where the report is written or whether prior reports are overwritten, but the safety/offline profile is well disclosed.

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 dense sentences with the capability first and the safety constraint second; every clause carries information (scope, mechanism, output, safety). No filler or restatement of the tool name.

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, and the offline/non-mutating profile is covered. What remains missing for correct invocation is parameter meaning (sbom, device_info) and where the evidence report lands, which matters because the tool's side effect is the deliverable.

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% across three parameters, so the description must compensate and largely does not. 'Local source/APK/IPA' hints that target is an artifact path, but sbom and device_info are left entirely unexplained in both schema and description, including their expected format and why they would be supplied.

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 (Inspect), a specific resource class (local source/APK/IPA), the mechanism (cached intelligence), and the outcome (saved evidence report). It implicitly separates itself from audit_start/audit_reassess by emphasizing 'local' and offline operation, but never names a sibling 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?

'No network or device mutation' functions as an implicit boundary condition, steering the agent toward this tool for offline artifact inspection. However, there is no explicit when-to-use vs audit_start or audit_reassess, and no stated prerequisites (e.g., whether intelligence_sync must run first).

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