Create multi-output

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

The description richly discloses behavior beyond annotations: it creates cropped slices, resizes to projector resolution, ends on Null, handles edge blending with GLSL feather, and optionally creates borderless Window COMPs. Annotations only indicate non-read-only, non-destructive, and open world; the description adds critical operational details. No contradictions.

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 four sentences long, front-loaded with the core purpose, and every sentence adds essential information. It efficiently covers purpose, edge blending mechanics, and window behavior without extraneous detail. The structure is clear and scannable.

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?

Given the tool's complexity (7 parameters, no output schema), the description covers key behavioral aspects: creation of Null nodes, edge blending technique, and as_windows state. It mentions that windows are left closed and should be opened in Perform mode. However, it does not describe the return value or what the tool actually outputs (e.g., path to created network), leaving a slight gap for an agent needing that detail.

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?

With 86% schema coverage, the description adds value for most parameters: explains source_path (master TOP), count (number of outputs), layout (slicing direction), overlap (edge blending with typical values), resolution (per-output resolution), and as_windows (borderless window creation). The parent_path parameter is not described, but it's a minor default. Overall, the description meaningfully enriches parameter understanding.

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 clearly states the tool's action: 'Fan a master TOP across N projectors/displays' and specifies it as the multi-projector counterpart to setup_output. It identifies the resource (master TOP) and outcome (cropped slices resized to full projector resolution, ending on Null). This distinguishes it from siblings like setup_output.

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 explains when to use the tool: for distributing a master TOP across multiple projectors with optional edge blending. It mentions setup_output as the single-window counterpart, providing some context for selection. However, it lacks explicit exclusions or comparisons with other sibling tools like create_dome_output or create_projection_mapping, which could help an agent choose more precisely among 92 siblings.

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