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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: live_models triggers a live query against the account's own provider key, and `prices` is only populated for models a public pricing page lists, which tells the agent to expect partial data. That caveat work is genuine added value, though it stops short of saying whether the live call can be slow or fail per-provider.

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?

The [read] tag and the purpose clause are front-loaded, and every clause carries information. The single run-on sentence enumerating ten response fields is dense and hard to scan, which costs it a point, but nothing is truly redundant given there is no output schema.

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 no output schema and zero schema description coverage, the description compensates fully: it documents the return item shape field-by-field, the provider enum, the live_models side effect, and the correct identifier to pass downstream. Nothing an agent needs to call this correctly and use the result is missing.

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% and the provider property has no enum in the schema, so the description carries the full burden — and it does, enumerating all sixteen allowed provider values inline and defining live_models' effect on the response. It also disambiguates the identifier type (account_uuid vs numeric account_id), which is not encoded anywhere in 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?

The description states a specific verb+resource (list the merchant's image-generation AI accounts) and scopes it precisely with '`image_ai` of the picture tools, the AI account of a character', which distinguishes it from sibling listers like list_ai_accounts, list_motions_ai_accounts and list_voices_ai_accounts. An agent knows exactly which account family this returns without opening any schema.

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 gives clear operational context: '(omit for all)' on the provider filter, 'live_models=true also asks the account's own key', and the strong warning 'Pass the `account_uuid` (a UUID), never the numeric account_id.' It never explicitly names a sibling to use instead when the target is a motion/voice/text account, so the when-not guidance is implied rather than stated.

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