audit_start

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, covering the safety profile. The description adds value beyond that by revealing this starts a persistent background job that must be polled rather than returning results inline, a trait absent from the structured fields.

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?

A single front-loaded sentence that states the action first and then the follow-up routing. No filler, no redundancy.

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?

Output schema exists, so return values need not be explained, and annotations carry safety. However, with three undocumented parameters at 0% schema coverage, the definition leaves an agent guessing about sbom and device_info, a meaningful gap for a kickoff 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% and the description adds no information about any of the three parameters (sbom, target, device_info). With low coverage the description was expected to compensate, and it provides nothing on parameter meaning or format.

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 (Start) and resource (audit) with a differentiating scope marker, 'persistent offline', that separates it from the one-shot audit_scan sibling. It does not open the schema to tell them apart, but the phrasing makes the async/background nature clear.

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?

Explicitly routes the agent to jobs_status for progress and jobs_cancel to stop, which is useful lifecycle guidance. It does not address the more important selection question of audit_start vs audit_scan or audit_reassess, so it stops short of full alternative coverage.

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