audit

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

Annotations already declare readOnlyHint=true. The description adds value by explaining the types of violations (hard vs soft) and that soft violations generate open questions. It also mentions auto-skip behavior. This adds useful behavioral context beyond the annotation.

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 relatively concise (4 lines) and front-loaded with purpose. However, it mixes Japanese and English, and could be more structured (e.g., list parameters). Still effective and not 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?

Given 3 parameters and no output schema, the description covers the core purpose and two parameters, but fails to explain 'as_of_chapter' or the return format (what violations look like). It provides use cases but lacks completeness for seamless 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?

Schema coverage is 0%, so description must explain parameters. It explains 'branch' (entire branch) and 'include_soft' (enables semantic contradiction detection with NLI, auto-skip if model missing). However, 'as_of_chapter' is not explained, leaving a gap.

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 states it audits the entire branch for deterministic and semantic contradictions. It distinguishes from siblings like 'check_constraints' (which checks constraints) and 'list_open_questions' (which lists questions, while this tool generates them). However, a more explicit distinction could improve clarity.

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 provides usage context: 'used for sanity check after import or after writing a chapter.' It also explains behavior when include_soft=True and model is unavailable (auto-skip), but lacks explicit when-not-to-use or comparison to alternatives.

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