research_record_settlement_decision

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

Annotations already declare this as a non-readonly, idempotent, non-destructive write, so the description does not need to restate that safety profile. The description adds meaningful behavioral constraints: every objection from both rounds must be addressed with evidence, unsupported conclusions must be preserved, experiments must be bounded, and FAIL_CLOSED provider-failure gates cannot be cleared through this tool. This is valuable context beyond what the annotations or schema provide.

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 sentences, and each sentence earns its place: purpose, required timing, content obligations, and the fail-closed exception. The core purpose is front-loaded before policy details and alternative routing. There is no filler or redundant restatement of schema information.

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?

This tool has a complex nested decision schema, but the description supplies the missing policy context: when the call is required, what content obligations apply, and which gate failure must be routed to rva_retry_unavailable_review. The schema already documents structure, enums, required fields, and additionalProperties constraints. No critical invocation information is absent.

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 carries the burden, and it compensates well for the nested decision object: 'Address every objection... with evidence, preserve unsupported conclusions, and bound any experiment' maps to objections, evidenceRefs, unsupportedConclusions, and experimentBudget. It also links 'bound to the latest settled gate outcome' to outcomeId. It does not explicitly discuss task_id, but the parameter name and UUID schema make its role unambiguous.

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 verb 'Record' names the action and the object: 'the orchestrator's content-based conclusion and next step, bound to the latest settled gate outcome.' It clearly distinguishes this from review/follow-up/retry siblings by specifying a distinct record-keeping operation with a specific trigger condition. This is not a tautology and gives the agent a concrete sense of what the tool does.

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?

It explicitly states when the tool is required: 'after scientific RVA budget exhaustion before publication, closure, or next execution.' It also provides an explicit exclusion and alternative: 'A decision cannot clear a FAIL_CLOSED provider-failure gate; use rva_retry_unavailable_review after provider recovery.' This gives the agent clear selection guidance versus a sibling tool.

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