audit_draft

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

No annotations are present, so the description carries the full burden. It discloses neither the return format nor whether the tool is read-only or has side effects. The input-format warning is useful but is not a description of the tool's behavior or outcomes.

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 two sentences, front-loaded with the core purpose and followed by a critical input instruction. Every sentence has purpose, and the all-caps warning is salient without being verbose.

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?

With no output schema and no annotations, the description should explain what the audit returns or at least mention the optional case_json parameter. It does neither, leaving an incomplete picture for an agent deciding whether this tool covers the needed functionality.

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 coverage is only 50%; the optional case_json parameter is not described in the schema nor in the description. The description reinforces draft_text's plain-text requirement, but the undocumented case_json remains a gap that hurts parameter understanding.

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 names a specific verb ('audita') and a specific resource ('un borrador ARCO'), and enumerates the concrete audit targets (wrong authority, misused articles, imprecise sanction threats). This clearly distinguishes it from other audit siblings like audit_identity or source_audit, which focus on different aspects.

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 does not state when to use this tool versus the many sibling audit tools. It does give an important input-format guideline (pass plain text, not JSON), which helps invocation but not tool selection or alternative comparison.

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