normalize_sprite

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

With no annotations, the description carries the full burden. It discloses non-destructive behavior ('without overwriting the source') and notes it writes output and metadata. However, it does not mention file format handling, potential failure modes, or whether multiple frames are processed from a single file or multiple files, leaving ambiguity.

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, tightly written sentence that front-loads the core action and outcomes. It avoids unnecessary words and effectively communicates the essential purpose in a compact form.

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?

For a tool with six parameters, three required, and no output schema, the description is underspecified. It does not explain the manifest file purpose, how the input file represents multiple frames, the meaning of pivot options, or the effect of padding on the output. An agent would likely need to inspect the schema or other tools to use this correctly, making it incomplete.

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. It mentions 'shared alpha bounds', 'deterministic padding', and 'pivot metadata', giving context for the input, padding, and pivot parameters. However, it does not explain the role of manifest_filename, the format parameter, or how multiple frames are referenced, so the agent must rely on schema enums and names.

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 action ('crop'), the resource ('raster frames'), the outcome ('shared alpha bounds, deterministic padding, pivot metadata'), and a key behavioral guarantee ('without overwriting the source'). It clearly differentiates from sibling tools like crop_canvas or generate_sprite_anchors by focusing on normalization for multiple frames.

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 implies when to use the tool (when you need to normalize frames to alpha bounds and add padding), but it does not explicitly mention alternatives or exclusion criteria. It lacks guidance on when to prefer this over crop_canvas or other related tools, leaving some inference to the agent.

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