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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds genuinely new behavior: results are ordered cheapest-first, each entry carries a per-call coin cost, and the default model choice per media type. It does not describe result volume or whether the list is exhaustive, which is a minor gap.

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 dense sentences, front-loaded with what the tool returns, then when to call it, then the default/escalation policy. No filler and no repetition of the title or annotations.

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?

For a zero-parameter, read-only list tool with no output schema, the description covers everything needed: what is listed, how it is ordered, what each entry contains (coin cost), and how to use the result to pick a model. Safety is already carried by annotations.

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?

The tool takes zero parameters, so the schema baseline is 4. The description still contributes model-level semantics (the per-media-type defaults) that shape how the caller should act on the returned list.

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 ('List Dora generation models') plus two distinguishing traits: cheapest-first ordering and per-call coin cost. An agent can tell this apart from generate_image/generate_video/check_job at a glance.

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?

Explicitly names three triggering conditions (user asks what models exist, cost matters, verifying a model name) and gives an escalation rule with named defaults (nano_banana_2 for images, seedance_1_5_pro for videos) plus the condition for stepping up. Nothing is left to inference.

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