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

Annotations already declare readOnlyHint and openWorldHint, but the description adds genuinely new behavioral facts: deterministic, retrieval-first, ~2s latency, no language model runs, and a no-invention guarantee when corpus coverage is thin. That is real context beyond the structured fields; only a note on cost/rate limits or result size is missing.

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?

Front-loaded: the core action and output shape come first, caveats and the 'does not decide' boundary come last. The colon-delimited section list is dense but each item conveys a distinct output component, so no sentence is wasted.

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?

There is no output schema, so the description carries the burden of describing the return value — and it does, enumerating the brief's five components plus the honesty behavior when coverage is missing. Adequate for a single required parameter, read-only tool; only sibling routing is unaddressed.

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%, so the schema already explains draft, goal, focus, stakes, and max_sources including the default and clamping behavior. The description's list of brief sections loosely hints at what 'focus' selects, but adds no syntax or interpretation beyond the schema — 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: turning a DRAFT claim/decision/plan into a 'bounded, provenance-preserving inquiry brief', and enumerates exactly what the brief contains (shared ground, attributed tensions, missing evidence, falsifiable questions, one next evidence move). An agent knows precisely what the tool produces, though no sibling is named to sharpen the contrast with omnarai_divergence or omnarai_council.

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?

Usage is implied by the input framing — bring a draft claim you want challenged — and the closing 'Informs an investigation; does not decide' sets a boundary on what to do with the output. However, with 13 sibling tools including omnarai_divergence and omnarai_council, no alternative is named and no condition selects this over them.

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