paint_pixels

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

With no annotations, the description carries the full behavioral burden. It discloses side effects ('Writes the design layer only; refreshes refs/<slot>_ref.png') and the follow-up action of reading preview_paths. It omits failure/error behavior and permission requirements, but it is transparent about mutation and scope.

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 compact and logically ordered: target path, item format, coordinate semantics, side effects, follow-up, and forbidden alternatives. Every sentence contributes information with no filler.

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 provides strong operational detail and the output schema covers return-value structure. However, given six parameters and zero schema description coverage, the unexplained required 'name' parameter and the relationship to sibling pixel tools leave an agent with non-trivial ambiguity.

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 coverage is 0%, so the description is the only source of parameter meaning. It usefully explains the 'pixels' item structure and color formats, and implies 'slot' through the path, but it leaves the required 'name' parameter and the optional 'scale', 'plan_id', and 'output_dir' parameters unexplained.

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 ('Paint') and a precise target ('design/layers/<slot>.png') plus the required paint path, so the agent understands the primary action. It does not explicitly differentiate this tool from sibling pixel-editing tools like set_pixels or paint_from_commands, though the wording 'individual pixels' and 'design layer only' narrow the scope.

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?

It gives clear operational context: this is the designated pixel-painting path, it should be followed by reading preview_paths, and Shell/PIL and GenerateImage are explicitly forbidden alternatives. It does not explain when to choose this over closely related sibling tools such as set_pixels, fill_rect, or clear_rect.

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