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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered by structured data. The description adds two things annotations cannot: that spec_version is required downstream to edit, and a prompt-injection warning that the text originates from an analysed website and must be treated as data — a meaningful behavioral disclosure for an agent consuming untrusted content.

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?

A single dense sentence plus a short safety clause — front-loaded with the resource, then the edit-workflow hint, then the security warning. The parenthetical field list is heavy but earns its place because there is no output schema to carry that information.

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?

With no output schema, the description takes on the burden of describing return values and does so by enumerating scenes, CTA, voice, music and spec_version. Combined with the injection warning and the edit prerequisite, an agent has enough to call it and handle the result; only behavior on a missing/invalid video_id is unaddressed.

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?

There is one required parameter, video_id, with 0% schema description coverage, and the description never mentions it or explains where to obtain it. The uuid format makes its meaning largely self-evident, so this is not a severe gap, but the description adds no semantic value over the schema for the sole input.

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 names the exact resource (a video's storyboard) and enumerates its contents — scenes in order, CTA, voice, music, spec_version — so the agent knows precisely what comes back and can distinguish it from get_video or update_storyboard. It loses a point only because it is phrased as a noun phrase rather than an explicit verb ("retrieve the storyboard for a video").

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?

Usage is only implied: the parenthetical "spec_version (needed to edit)" signals a read-then-edit workflow with update_storyboard, which is a genuinely useful hint. But there is no explicit statement of when to call this versus get_video or approve_storyboard, and no prerequisites or error conditions are given.

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