quality_presets

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

With no annotations, the description carries full responsibility, and it excels. It discloses that omitting 'rad_params' inherits a preview-grade default and quantifies the accuracy impact with a concrete example (sDA 77.78% vs 100%). It explains the behavior of calling with no argument versus a level, and it lists each level with its exact -ab value and caveats. No hidden behavior is omitted.

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 description is long but every sentence earns its place. It front-loads the purpose, explains why ambient quality matters, lists levels with concise caveats, and ends with usage instructions. The structure is logical and scannable, with no fluff or repetition.

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 description covers everything an agent needs: what the tool does, the trade-off it addresses, all valid inputs, the output behavior (table vs single level), and how to integrate with simulation tools. Given the tool's simplicity (one optional parameter) and the presence of an output schema, this is complete. The agent can confidently invoke it without additional context.

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?

The schema only defines a single optional 'level' parameter with no description or enum, so schema coverage is effectively 0%. The description fully compensates by enumerating the valid values (low, medium, high, extra_high) and explaining what each does. It also clarifies the null/omitted case, making the parameter's meaning completely clear.

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 opens with a precise purpose: 'Ambient-quality presets: pick the accuracy/runtime trade-off up front, by name.' It clearly distinguishes this tool from siblings like 'presets' and 'list_presets' by focusing specifically on ambient-quality levels for Radiance. The description immediately tells the agent what the tool is for and what it returns.

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 description gives explicit guidance on when to use each level: low for geometry checks, medium for drafts, high for reportable results, extra_high for validation. It also explains how to call it with or without an argument and how to pass the level to simulation tools. While it doesn't explicitly state alternatives, the level list and integration instructions provide complete context for selection.

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