preview_brief

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: a specific output path, directory creation, running Scripts/sim_store_prep.sh, invoking xcrun simctl recordVideo, and the 'real footage only' constraint. It omits idempotency/overwrite behavior, whether the recording step blocks or times out, and what happens if the brief already exists.

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?

Front-loads the primary artifact (BRIEF.md path) before the follow-on steps, which is good, but it is a single dense run-on sentence mixing file paths, shell commands, and skill invocations. Sized plausibly for the complexity yet hard to scan.

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?

Output schema exists so return values need not be described, but for a multi-step tool with no annotations and 0% parameter coverage the description still leaves gaps: no permission/prerequisite context, no failure behavior, and no guidance on how the record and author steps interact with the schema defaults.

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 description coverage is 0% and none of the three parameters (app_dir, message, overwrite) are named or explained in the description. 'This app's App Preview' loosely implies app_dir, but message and overwrite are entirely undefined, leaving the agent dependent on an undocumented schema.

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?

Names a concrete verb and artifacts: writes marketing/preview/BRIEF.md, creates recordings/<locale>/, records the app, and authors video via the hyperframes skill. This clearly separates it from siblings like preview_check or preview_upload. The only weakness is that it bundles multiple distinct actions into one tool, so the single 'what it does' is a pipeline rather than one operation.

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?

No statement of when to use this versus siblings such as preview_check, preview_review_sheets, or design_record_upload, and no prerequisites or exclusions. The pipeline position ('then record... and author...') is implied but never framed as guidance for an agent choosing between tools.

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