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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses two things the annotations cannot: that the call is free ("Spends nothing") and that it can return clarifying questions instead of results when community or gender is absent. That conditional, non-happy-path return is exactly the kind of behavior an agent needs to plan a retry loop. It stops short of describing what happens on an invalid or over-long brief.

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, front-loaded with the transformation and its outputs, then the exception path, then the cost guarantee. No filler and nothing buried; the most decision-relevant fact for an agent (it costs nothing) is placed last for emphasis without harming scanability.

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 present, the description does not need to enumerate return fields, and it correctly summarizes them at a high level plus flags the questions response. For a 6-parameter, one-required planning tool in a 28-sibling namespace, the main shortfall is the absence of any explicit routing to generate_image as the natural next step.

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 83%, so the schema already documents brief, count, aspectRatio and ethnicityKey well. The description's contribution is explaining the question-answer loop for community/gender, but that largely restates what the schema already says ("The human's answer to the gender question", "from an earlier plan_shot question"). No added detail on resolution or aspectRatio precedence beyond the schema's own note.

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?

"Turns a one-line brief ... into image selections, a preview and the credit cost" names a specific verb (plan/turn into) and concrete outputs, so the agent knows this is a planning step rather than a generation step. The domain scope (Indian people, clothing, food, festivals, weddings, places, crafts) further narrows it. It never names the sibling it differs from (generate_image / preview_generation), so differentiation is inferred from "Spends nothing" rather than stated.

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 phrase "Spends nothing" and the note that a brief missing community or gender yields questions together imply this is the free pre-step before a paid generation. However, there is no explicit "call this before generate_image" instruction, no statement of when to skip it, and no named alternative for users who already have an image plan.

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