Validate Study Recipe

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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered; the description adds genuinely new behavioral detail about what the inspection block carries (gate on inert prior fields, engine state, lineage with dataset availability). It also notes dataset availability is 'checked now and never inferred,' which is useful non-obvious behavior, though much of the return-shape detail is duplicated from the richer schema description.

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 rest enumerates what is returned. It is a single long sentence with a dense parenthetical, which costs a little readability, but every clause carries information and nothing is redundant 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 single-parameter, read-only validation tool with an output schema present, the definition covers purpose, decision context, and the shape of the inspection payload. Return values need not be spelled out given the output schema, so remaining gaps are minor.

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 100% and the single nested specification parameter is documented in depth (api_mmm vs model_snapshot constraints, rejected keys, review-only limits). The description adds no parameter-level meaning beyond the schema, so the baseline 3 applies.

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?

Opens with a specific verb+resource pair ('Resolve and validate a recipe') and immediately scopes it against the obvious write-path siblings by stating 'without creating a run.' An agent can distinguish this from create_study_recipe, revise_study_recipe, and launch_study_run without opening any schema.

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 a clear decision context: use it to 'check for inert fields and an unavailable dataset before freezing,' which implies the pre-commit checkpoint role. It does not explicitly name the alternative tool to use once validation passes (e.g., create_study_recipe/launch_study_run), so it stops short of full when/when-not routing.

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