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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety burden is light. The description adds two genuinely non-obvious traits: an account/sign-in requirement enforced by the host, and the pricing rules (all models usable with any credits, video priced per second).

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 short sentences with zero filler; the catalog scope and pricing model come first, and the prerequisite (account sign-in) is saved for the end where it acts as a call-out.

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 no explanation, and the description covers auth and pricing quirks that the schema does not. It leaves slightly unclear whether the conversation_id handshake is mandatory for a read-only listing call, which is the only meaningful 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?

Schema description coverage is 100%, including the kind enum and elaborate context/llm_model/conversation_id guidance, so the schema does the heavy lifting. The description mentions both image and video catalogs but adds no syntax or filtering guidance beyond that, making 3 the correct baseline.

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 the resource (image and video models with per-tier credit price) and ties it to the sibling operations it feeds, generate_image and create_video. The stated purpose is clear, though it is phrased as a noun phrase rather than saying outright that it returns a browsable catalog.

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?

The link to generate_image / create_video implies this is a pre-generation model-selection step, but the description never states when to call it versus just calling generate_image directly. No exclusions or alternative tools are named.

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