Normalise an AI evaluation answer

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

The description adds context beyond annotations: it specifies the tool is non-persisted, deterministic, and never accepts hidden reasoning. Annotations already mark it as readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the description reinforces and elaborates on these traits, providing useful behavioral clarity.

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?

The description is a single sentence that effectively front-loads the core purpose (validate, deterministic, non-persisted) and lists accepted inputs. Every phrase adds value with no redundancy.

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?

Given the complexity (11 parameters, 8 required, no output schema, nested objects), the description is insufficient. It does not explain the structure of the return envelope, the meaning of required parameters, or how inputs like task_id, chosen_record_id, and considered_record_ids should be used. The absence of output schema makes this gap more critical.

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?

With 0% schema description coverage, the description carries full responsibility for explaining parameters, but it only mentions 'visible answers, evidence and caveats,' corresponding to answer, evidence, caveat_ids. Eleven parameters exist, including key ones like task_id, chosen_record_id, considered_record_ids, alternatives, mcp_plan, contrasts, substitution, confidence, all unexplained.

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 clearly states the tool's function: 'Validate and return a deterministic, non-persisted evaluation envelope.' It specifies what it accepts (visible answers, evidence, caveats) and excludes (hidden reasoning), distinguishing it from siblings like okf.get_record, okf.compare, and okf.prepare_mcp_plan, which serve different purposes.

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 no guidance on when or when not to use this tool versus alternatives. No explicit context for usage, prerequisites, or exclusions are mentioned, leaving the agent to infer when submit_answer is appropriate given the sibling tools.

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