Make variations of one image

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

Annotations already signal mutation and non-idempotence, so the description's job is lighter. It adds valuable context beyond annotations: GPU cost, mandatory confirm, grid-order stability matching list_jobs/download_job, and the practical difference between subtle and strong variations. No contradiction with annotations.

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?

Every sentence earns its place: main action, iteration rationale, subtle/strong behavior, index mapping, and cost/confirm warning. It is front-loaded with the core purpose and wastes no words.

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 7-parameter tool with no output schema, the description plus the rich input schema cover the essentials: what to pass, how iteration works, how indexing behaves, and why confirm is required. The wait parameter in the schema describes return behavior, so the description need not re-explain it. A minor gap is the lack of explicit guidance about asynchronous queue behavior for relax speed, though the schema covers speed semantics.

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 baseline is 3. The description goes beyond the schema by explaining the zero-based index as matching the ordering from list_jobs and download_job with explicit positions, and by translating subtle/strong into behavioral outcomes. This adds real selection semantics beyond raw parameter descriptions.

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?

Description opens with a specific verb and resource: 'Take one image from a finished grid and generate four variations of it.' It grounds the tool as the Vary button and explains its role in iteration, clearly distinguishing it from generating a fresh set or related siblings like rerun_job or imagine.

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 explicitly frames when to use the tool: iterate on the closest result and push it further 'rather than rolling a fresh set.' It also explains the subtle/strong choice and confirm requirement. However, it does not explicitly name sibling tools like imagine or rerun_job as the alternatives, leaving some routing to inference.

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