system_audit

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

With no annotations, the description carries the burden and does disclose the audit scope, optional devil's advocate behavior, and EU-AI-Act-style record output. However, it does not state whether the audit is read-only, what side effects it may have, or what the record format looks like.

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?

Three concise sentences pack the core purpose, parameter behavior, and record style without redundancy. Information is front-loaded and every clause contributes.

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 no output schema and no annotations, the description provides a solid overview but lacks return format details and any usage context relative to doctor/devils_advocate. The EU-AI-Act Article-12 reference is cryptic and may not fully inform an agent of the expected output.

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?

The schema only provides a boolean with default, and schema coverage is 0%. The description compensates by explaining devil=true behavior ('runs the devil's advocate over every failing finding'), though it leaves the false case implicit.

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 identifies the tool as a full-system audit covering memory inventory and specific invariants (append-only integrity, bi-temporal ordering, canon presence, dangling supersede pointers). It is distinct from memory retrieval/mutation siblings, though it does not explicitly contrast itself with doctor or devils_advocate.

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 implies use for system-level audit and invariant checking but does not state when to prefer it over alternatives or provide exclusions. No explicit when/when-not guidance is given.

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