process

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

With no annotations, the description carries the full burden and does well: it discloses the write target, that processing is non-destructive/repeatable (always starts from raw), and that multi-asset calls are processed uniformly. It omits permission/auth needs, overwrite behavior, and what 'preview' actually does.

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?

Four tight sentences, front-loaded with purpose and output before the batching rule and recipes. The telegraphic recipe syntax is dense but earns its place by giving copy-ready pipelines; 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?

For a complex nested-tool with no output schema and no annotations, the description covers the write path, repeatability, batching semantics, and two canonical pipelines. It leaves gaps around the 'project' and 'preview' parameters and error/partial-failure behavior, but nothing critical to a first correct call is missing.

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?

Top-level schema description coverage is 0%, so meaning must come from the description or nested fields. The description explains 'assets' (one or more), 'steps' (ordered), and gives two concrete recipes that map op sequences (remove_bg, trim, outline, fit 512 / remove_bg, trim group, pixelate shared), but never addresses 'project' or 'preview'.

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?

States a specific verb and resource ('run steps, in order, on the RAW files of one or more assets') plus the concrete output path 'processed/<name>.png'. This clearly distinguishes it from siblings like ingest, slice_grid, or build_spritesheet, which operate elsewhere in the pipeline.

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?

Gives explicit when-to-use context ('Always starts from raw, so re-run with new settings freely') and a batching rule ('Pass every asset of a set in ONE call with the same steps'). It does not name alternative sibling tools or state when to choose them, so it falls short of a 5.

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