still_grade

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

No annotations exist, so the description carries the full behavioral burden. It usefully discloses that the LUT is applied last and that signal_mode marks the LUT as signal-alignment and records near-black/near-white deltas, but it never states that files are written, whether output is destructive, or what preconditions (e.g., existing output_dir) are required.

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?

Front-loaded with the pipeline stage order, then the signal_mode caveat, then a clean args list. Every line carries information; no padding or restatement of the tool name.

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?

An output schema exists, so return values need not be explained. For a no-annotation write tool the description covers pipeline order, key behaviors, and all params adequately, though it omits file side effects and overwrite semantics.

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 supply all parameter meaning. It lists all five params with usable context (absolute paths, hero for match stage, .cube/.3dl applied last, signal_mode semantics), genuinely compensating for the empty schema — though 'hero still for match stage' is somewhat circular.

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 (grade) and resource (stills) plus the pipeline order correct→match→look, which is more than the bare name conveys. It doesn't explicitly contrast itself with siblings like still_match or still_gate, but the pipeline framing makes its scope inferable.

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?

No when-to-use or when-not guidance is given, and no alternatives are named despite the presence of still_match, still_gate, and still_package as siblings. The agent must infer from the pipeline description that this is the full grader versus stage-specific tools.

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