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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds substantive context beyond that: credit estimates are returned, settings_schema exposes the valid settings keys, is_default reflects the account's saved choice falling back to Framesail's, and entity_backed=true sections cannot be overridden here and must be changed via edit tools — a real mutability boundary.

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?

It is information-dense and front-loaded with the core purpose, with no filler sentences. The parenthetical packing ('settings_schema (the valid settings keys)') and fragmentary opening slightly reduce readability, but every clause carries useful signal.

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?

There is no output schema, so the description must explain the return values, and it does: model lists with credit estimates and settings schema, the is_default flag, and prompt_sections with their entity_backed semantics. The top-level response shape is not spelled out, but the fields an agent needs to act on are covered.

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, but the description genuinely elaborates: it explains what is_default means, what settings_schema contains, the model-family concept behind provider/talking_head, and the entity_backed flag that governs editable_sections. That is added meaning beyond the enum descriptions 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 makes clear this is a discovery/read tool returning the options a generate call can accept (allowed models with credit estimates, settings schema, prompt sections), which cleanly separates it from the many *_generate siblings that actually produce assets. The opening sentence is a fragment ('What a generate call can be told to use') rather than a verb+resource statement, so it is clear but not maximally crisp.

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 conditional guidance tied to the parameters ('pass provider or talking_head for one family') and routes the agent to the alternative tool set for a specific case ('entity_backed=true sections ... change it with the edit tools'). It does not explicitly say when not to use this tool or that it should be called before a generate call, but the context is clear.

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