Preview Review Sheets

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

Annotations already declare the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false). The description adds meaningful context beyond that: it writes files via ffmpeg, produces three named artifact types, and emits a per-locale path map. It does not say where files land on disk, but the behavioral picture is solid.

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?

Tightly structured with front-loaded purpose, a labeled 'Use when:' clause, and a labeled 'Returns:' clause. Every sentence earns its place and no filler is present.

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 one-parameter generation tool with an output schema, the description covers purpose, artifacts, prerequisite (a rendered preview), the downstream step, and the return shape. Nothing an agent needs to invoke it correctly is missing.

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?

Only one parameter (app_dir) and schema description coverage is 100%, so the schema fully documents the argument including the app.spec.json hint and an example path. The description adds nothing about parameters, which is the expected baseline when the schema carries the burden.

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?

States a specific verb (generate) and enumerates the concrete artifacts produced (contact sheet, phone-size sheet, transition strip), scoped to 'every final preview'. This clearly separates it from siblings like preview_brief, preview_check, and the follow-up preview_review_log.

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?

Provides an explicit 'Use when: reviewing a rendered preview' trigger plus the workflow ('open the sheets, score them, then call preview_review_log'), which routes the agent to the correct next tool. No explicit when-not conditions or named alternatives for the review stage, so it stops short of a 5.

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