draw_text

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

The description says 'Rasterize and draw text into a sprite layer and frame,' which implies a mutating operation, but does not disclose whether the sprite is permanently modified, whether previous text at that location is overwritten, what happens if the layer doesn't exist, or that create_if_missing defaults to true. With no annotations provided, the description carries the full burden but still communicates the core action, avoiding outright misleading behavior.

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 a single concise sentence with no filler, front-loading the core verb 'Rasterize and draw.' It is efficient, but it is so short that it sacrifices valuable explanatory content about the many parameters and behaviors, so it earns a 4 rather than a 5.

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?

This is a complex tool with 20 parameters, 5 required, no output schema, and no annotations. The single-sentence description does not explain return values, side effects, error conditions, or how parameters like anchor, shadow, outline, and create_if_missing interact. Without annotations or an output schema, the description must carry more weight, and it clearly falls short for a tool of this complexity.

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 description coverage is 0%, so the description must compensate for the 20 parameters, but it adds no parameter-level meaning whatsoever. It does not explain text positioning, anchor semantics, color formats, shadow/outline behavior, font usage, or frame indexing. The schema itself provides types, defaults, and enums, so the description adds no value beyond what structured data already provides.

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 states a specific verb and resource: 'Rasterize and draw text into a sprite layer and frame.' This clearly identifies the operation and target, distinguishing it from sibling draw tools like draw_line and draw_rectangle. However, it does not explicitly differentiate from related text tools like measure_text or list_text_fonts, so it earns a 4 rather than a 5.

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?

There is no guidance on when to use this tool versus alternatives such as draw_pixels_at, draw_rectangle_at, or measure_text. It does not mention prerequisites (e.g., sprite must exist, layer must exist, font must be available) or related tools like list_text_fonts for finding available fonts or measure_text for sizing text. The agent is left to infer usage from parameter names alone.

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