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

Beyond readOnlyHint and openWorldHint, the description adds important credit-safety context by promising that nothing is spent. It also defines the preview's output scope and excludes the rendered TASVR wording, though validation behavior and whether the cost is exact or estimated remain unspecified.

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?

Two compact sentences front-load the outputs and zero-spend behavior, then provide a scope exclusion without repeating schema details. The undefined “TASVR” terminology makes the final caveat less clear than the otherwise efficient wording.

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?

The central preflight behavior is covered, and the output schema reduces the need for further return-value documentation. For such a deeply nested tool, however, important boundaries remain implicit: no explicit statement that an image is not generated, no estimate_cost comparison, and little guidance on the selection input.

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?

At 50% schema coverage, the description modestly clarifies that selection is resolved and reference roles are inspected, but adds no further input syntax or construction guidance. The detailed nested schema does most of the parameter documentation, making this adequate rather than strong.

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 gives a specific operation and outputs: resolving a selection into preset labels and reference roles while showing its credit cost. Differentiation from generate_image and estimate_cost is implicit rather than explicit, and it does not directly state that no image is produced.

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 title and “before anything is spent” clearly position this as a preflight step before generate_image. It does not route cost-only checks to estimate_cost or actual rendering to generate_image, so the guidance is useful but not exhaustive.

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