content-audit

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

With no annotations, the description carries the full behavioral burden and does so well: it declares read-only behavior, D&D 5e-only scope, the specific rules scanned, and a scope caveat that NPC biographies are not scanned for rule 12. It loses a point because it says 'five strict authoring-quality rules' but lists only four bullets, and it never describes the shape of the violation report.

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 long but tightly structured and front-loaded: purpose and safety first, then a scannable bulleted list of rules, then usage trigger and targeting semantics, then concrete remediation steps. Every sentence earns its place, and the length is justified by the number of distinct rules and options an agent must understand.

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?

For a complex, zero-annotation tool with no output schema, this is unusually complete: it names all scan rules, distinguishes player-visible item descriptions from GM-facing NPC biographies, describes full-sweep behavior, and tells the agent how to fix findings. The main missing piece is the exact return/report structure, which would help an agent consume and act on the results automatically.

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 input schema already describes all three parameters fully, so the baseline is 3. The description adds operational meaning beyond the schema: actorIdentifiers refers to the NPCs just built with their gear/features, itemFolders maps to the loot folder, and omitting all targets triggers a full sweep. This is enough to move above baseline, though the schema already covers the literal parameter meanings.

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 opens with a specific verb-resource pair: 'scan documents for the five strict authoring-quality rules and report violations to fix,' and immediately disambiguates it from mutation tools with '(read-only; never mutates)'. It enumerates the exact rule categories, so an agent can clearly tell this audit tool apart from the many update/fix siblings in the namespace.

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?

It gives an explicit trigger: 'RUN THIS before declaring a build done.' It explains the targeting modes — 'Target what you built' with actorIdentifiers, itemFolders, or worldItemIds — and the no-target full-sweep behavior. It also names follow-up fix tools, giving the agent a clear workflow instead of leaving usage to inference.

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