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

Annotations declare write, open-world, idempotent, non-destructive; the description adds genuinely non-structured context: it consumes planning credits, returns specific artifacts (narration, factual review notes, references, credit estimate), and confirms it does not render media. That credit-spend disclosure is the kind of behavior an agent needs before committing.

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?

Three compact sentences, front-loaded with the core action and followed by cost/return/scope notes in a sensible order. 'Existing account access applies' is boilerplate and the weakest line, but overall there is little waste.

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?

The behavior is well covered (purpose, credit cost, scope, and output schema makes return values self-documenting). However, for a 19-parameter tool with near-zero schema description coverage, the description leaves the caller without guidance on most inputs, which is the primary gap.

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?

With 19 parameters and only 5% schema description coverage, the description carries the burden but adds almost nothing: it loosely implies 'script' and 'project' and gestures at 'confirmScriptApproved' via 'user-approved'. Parameters like voice_id, video_model, story_kit_id, visual_style, character_ids, caption_style_id and the model IDs are entirely unexplained in both schema and description.

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 and resource ('Create a vertical video storyboard') scoped to an approved script in an existing project, and the negative clause 'does not generate images or animate video' separates it from the generation_* tools. It stops short of naming sibling storyboard tools (get/revise/approve), so it does not fully differentiate the family.

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?

Clear preconditions are given: the script must be user-approved and the project must already exist, establishing when this tool is appropriate. It excludes adjacent behavior ('does not generate images or animate video') but does not point to a specific alternative tool for modifying or reading a storyboard once created.

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