Understand

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive behavior, so the safety profile is covered. The description adds provider capability constraints (mixed media on Gemini, image-only elsewhere), which is a genuine behavioral fact beyond the structured fields, but says nothing about limits or output behavior.

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?

Two tight sentences with the core action front-loaded and the provider caveat immediately following. No filler or redundancy.

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?

An output schema exists, so return values need not be described, and annotations cover safety. But for a 6-parameter tool with 0% schema coverage, the description leaves half the parameters unexplained (tier, model, provider, max_tokens), making it incomplete relative to the tool's actual surface.

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% across 6 parameters. The description only clarifies that media_urls is multi-URL and that a prompt accompanies it; it says nothing about tier, model, provider, or max_tokens, leaving four parameters entirely undocumented in both the schema and the 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?

The description names a concrete verb (understand) and resource (images and/or videos with a prompt), and clarifies multi-URL input. It is clear on its own, though it never names or contrasts with the sibling 'generate', so the agent must infer the distinction between understanding and generating media.

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 implicitly guides provider choice by noting Gemini handles mixed image+video while OpenAI/Grok are image-only, which is real usage context. However, it gives no guidance on when to use this tool versus 'generate' or any other sibling, leaving tool selection to inference.

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