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

Goes beyond the annotations by disclosing the return contract (model key, plus aspect ratio/resolution/duration with ask_params) and, importantly, host-dependent degradation to a text list. It does not say whether the picker blocks, what a cancel yields, or how long it waits, which matters for a UI-interaction tool with idempotentHint=false.

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?

Four short sentences, front-loaded with the action and the picker's nature, then usage, then exclusions, then return/fallback. No sentence is redundant.

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 an output schema and annotations present, the description need not explain return values, yet it does so usefully and covers the host fallback. The remaining gap is interaction semantics on cancel or timeout, which an agent calling a user-facing picker would benefit from knowing.

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 coverage is 100%, so the baseline is 3. The description adds downstream meaning for ask_params (it yields aspect ratio, resolution and duration) that the schema only restates as a prompt, giving a small lift above baseline; media and need are left entirely to the schema.

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: let the user choose an image or video model from a picker, and names the picker's content (logos, starting prices). It is clearly distinguishable from sibling model tools like list_models and get_model, which do not prompt the user.

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?

Gives both directions explicitly: use when the user has not named a model or asks to choose one, do not call when a model is already named. It also supplies a fallback path for hosts without pickers, so the agent knows what to do if the call degrades.

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