Apply AI Layout Verdict

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

With no annotations, the description carries the full disclosure burden and does so well: it lists concrete validation rules (paths must stay inside the project, destinations are limited to manuscript/bible/outline/drafts_raw, chapter lines must exist) and states the persistence target .story/layout-verdict.json. It does not say what happens on validation failure (error shape, whether an existing verdict file is overwritten), which is the remaining gap.

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?

It is a single dense paragraph that leads with the action and the upstream tool, then the validation rules, then the consumers and the revert path. Nothing is wasted, though the validation clause is packed tightly enough to require careful reading.

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 2-parameter write tool with no output schema and no annotations, the description covers the critical facts an agent needs: input provenance, enforced constraints, storage location, downstream effects, and rollback. Only the failure/error behavior is left unstated.

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 100% and the nested verdict object is well typed (kind enum, confidence 0-1, required reasoning, arcs/chapters/files arrays), so the schema does most of the work. The description adds real semantic context by explaining that the verdict is the AI's output from reading story_export_layout_brief and listing the constraints the server enforces on paths and destinations.

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 states a specific verb (nộp/save) and resource (layout verdict JSON), and ties it to its upstream producer story_export_layout_brief. An agent can immediately tell this apart from analysis tools such as story_scan_messy_project because it writes a persisted verdict rather than computing one.

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 names the downstream consumers (story_auto_refactor_structure, story_scan_messy_project) that will prioritize this verdict, and it explicitly states how to undo it: delete the file to return to the heuristic. That covers when to use it, what it affects, and how to opt out.

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