rva_review_next_experiment

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

Annotations are all false (readOnly, idempotent, destructive), so the description carries the full behavioral burden and does well: it discloses the at-most-two-rounds constraint, the immediate gate release on final rejection, and the preservation of objections. No contradiction with annotations. It leaves out auth requirements or reversibility, but the disclosed gate/round semantics are genuinely useful context beyond the structured fields.

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?

Three sentences with the purpose front-loaded in sentence one and workflow context following. It is compact with no redundancy, though the dense domain jargon (RVA rounds, 'releasing the gate', 'preserving objections') slightly reduces immediate readability for an agent without RVA context.

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?

As a mutation tool with no output schema, sparse annotations, and 0% parameter coverage, the description must compensate heavily but does not. It explains workflow sequencing well but omits what the response contains, what success/failure looks like, and any guidance on the complex proposal structure. For a tool with a highly nested required object, this is 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%, and the proposal parameter is a deeply nested object with 13+ fields (abstractionLevel, discriminativeValue, decisionUnlocked, cleanValidationDataCost, etc.) that are entirely unexplained. The description does not clarify any parameter's meaning, format, or how required fields interrelate. For a nested object of this complexity, the lack of parameter guidance is a severe gap.

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 opening sentence 'Record a next-experiment proposal' states a clear verb+resource pair. However, with siblings like rva_review_contract, rva_review_result, and rva_challenge_result present, the description does not differentiate what makes this proposal distinct from those review/challenge records, so it stops short of full sibling disambiguation.

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 provides genuine procedural guidance: a two-round cap per execution step, the final rejecting round's gate-release behavior, and an explicit ordering prerequisite ('record research_record_settlement_decision before linking execution'). This names a specific sibling prerequisite, though it never states explicit exclusions or alternative conditions, so it earns a 4 rather than a 5.

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