colors_inspect

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

No annotations are provided, so the description carries the full burden. It discloses that the tool lists colors sorted by frequency with luminance, and mentions it handles spritesheet cell dimensions (cellH/cellW) for PNG sheets. However, it doesn't disclose potential performance implications for large files, whether it reads from disk or memory, or any side effects (though it's clearly a read-only inspection tool). The description adds some behavioral context beyond the schema (e.g., the purpose of cellH/cellW), but lacks details on output format or edge cases.

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 two sentences, front-loaded with the core function (list colors by frequency with luminance) and immediately followed by the use case. Every sentence earns its place: the first states what it does, the second explains why it matters and what to look for. 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?

Given the tool's complexity (4 params, no output schema, no annotations), the description is fairly complete. It explains the purpose, the use case, and hints at the spritesheet handling. However, it doesn't specify the output format (e.g., list of hex codes with counts), which could be important for an agent to parse results. Since there's no output schema, the description could have mentioned the return structure. Also, it doesn't clarify whether 'files' accepts glob patterns or specific paths, which might be relevant. Overall, it's good but not exhaustive.

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 75% (3 of 4 parameters have descriptions). The description adds meaning by explaining the purpose of the tool's output (raw material for canon decisions) and how cellH/cellW relate to spritesheet handling. It doesn't explicitly describe the 'files' parameter beyond the schema, but the schema already covers it. The description compensates for the missing 'top' parameter description by implying it controls the number of colors listed (default 40), which is not in the schema. This adds value beyond the schema.

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 lists colors used in files, sorted by frequency with luminance, and explicitly frames it as raw material for canon_init/canon_learn decisions. This distinguishes it from sibling tools like sprite_measure or sprite_verify, which focus on dimensions or verification rather than color analysis.

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 provides clear context for when to use this tool: to spot near-duplicate colors, anti-aliasing noise, and map hexes to visual parts before defining regions. It implies this is a preliminary analysis step before canon_init/canon_learn, but doesn't explicitly state when NOT to use it or name alternative tools for other color-related tasks. The sibling list includes canon_init and canon_learn, which are the downstream consumers, but no explicit exclusion is given.

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