build_audit_plan

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

The description adds scope detail beyond the annotations (what the plan contains) and a sequencing constraint. But it never resolves the tension between 'Create ... risk register' and readOnlyHint=true — the agent cannot tell whether the plan is persisted as a new artifact or merely computed and returned, which matters for a tool whose annotations declare no mutation.

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 tight sentences, front-loaded with the primary action and followed by the artifacts produced and the ordering constraint. No filler; a little more length would have been justified for the parameter, but nothing present is wasted.

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?

No output schema exists, so the description should carry more weight on what is returned and whether the plan is stored; it only lists section names. Combined with an undocumented required enum parameter, the definition is adequate for orientation but leaves real gaps before invocation.

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?

There is one required parameter, deployment_patterns, with 0% schema description coverage and no help in the description — the description never mentions deployment patterns or what the enum values mean. With a non-trivial enum of seven AI system types, the description is needed to compensate and does not.

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?

Specific verb+resource: creates an audit plan and unverified risk register, and enumerates the artifacts produced (intake, source-scoped risks, control verification backlog). It implicitly separates itself from siblings like scope_risks and investigate_risk by being the plan-construction step, though it never names them.

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?

'after system classification' signals a prerequisite ordering, so an agent can infer this is the post-classify_system step. However, it does not explicitly name classify_system or state when to prefer scope_risks/propose_remediation instead, leaving selection guidance implied rather than stated.

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