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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: checks are 'the same code the lab judge runs', 'no model, nothing stored', and some drafts are rendered/measured or rendered frame-by-frame — signaling deterministic, server-side execution that may be slow. It also discloses the return shape (per-row met/not-met plus judge-only rows), which matters because there is no output schema; it does not mention latency or whether results are reproducible across edits.

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?

Purpose is front-loaded in the first clause and the when-to-use sentence follows immediately. The middle list of draft formats is long but each item disambiguates a real input type; only slight tightening (e.g. grouping the rendered items) would improve it.

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 three-parameter tool with a nested prior map, full schema coverage and no output schema, the description covers purpose, trigger, execution model, and return values. The remaining gap is minimal: it never links to the sibling that issues the receipt after a pass, leaving the learner's next step to be inferred.

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 100%, so the baseline is 3; the description earns extra by explaining what `prior` actually does — earlier labs' answers supply rows that cross-compare (the example 'a sound must be for an event on your brief'), which is a relationship the schema's per-key descriptions do not state. `draft` and `module` are not elaborated beyond the schema, which is acceptable given the schema already names the module source (list_curriculum) and example values.

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 opens with a specific verb and resource — 'Run a Slop Curriculum lab's exact checks on a draft' — and then enumerates exactly which draft artifacts qualify (game spec, sound recipe/pack, motion shot, SKILL.md, tool definition, verb/juice table, plan). That enumeration separates it from siblings like validate_cartridge (cartridges) and claim_lab_receipt (which presumably records a pass rather than checking one).

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?

'Use when a learner wants to know whether their JSON or file passes before they submit' gives a clear triggering condition and implicitly the pre-submission timing. It does not explicitly name an alternative or say when-not to call it (e.g. after a receipt is already claimed), so it stops short of full routing guidance.

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