get_composite_pixel

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

Given no annotations, the description discloses that it composites visible layers by flattening a throwaway clone, implying non-destructive read. It explains the visual outcome ('what the player actually sees') but doesn't explicitly state it has no side effects.

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 well-structured with a brief purpose, distinction from sibling, and a docstring. It is efficient but could be slightly more concise as the first line repeats some info from later.

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 purpose, usage, and parameters well, but given no output schema, it lacks specification of the return format (e.g., RGBA tuple). It is otherwise complete for a simple getter tool.

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 description includes an Args section with descriptions for all 4 parameters, adding meaning beyond the schema's titles and types. For example, it explains that x/y are sprite-global coordinates and frame_index starts at 1.

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 it reads the RGBA colour visible at a pixel, composite of all layers. It explicitly distinguishes from get_pixel_color which reads a single cel.

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 explicitly states when to use this tool (value/CVD QA on grouped/multi-layer scenes) and contrasts with get_pixel_color. However, it doesn't mention when not to use it or alternative tools beyond the one sibling.

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