Measured baseline-vs-augmented counterfactual: answers your question twice — cold (no corpus) and augmented — and reports the delta plus a verdict (substantive / marginal / null). Honest by construction. Runs as an async job (~35s): returns a job_id — poll with omnarai_job.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | The question to trace with and without the corpus. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the async nature, job polling, and the 'honest by construction' trait. It explains the counterfactual mechanism but does not detail potential side effects or authorization needs.
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 three sentences, each earning its place: first sentence states purpose, second explains mechanics, third provides async details. Front-loaded and free of fluff.
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?
Despite having no output schema, the description covers input, process, output (delta and verdict), and follow-up action (polling). It does not cover error cases or permissions, but for a simple trace tool these are minor omissions.
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 coverage is 100%, so baseline is 3. The description repeats the schema's parameter meaning ('the question to trace with and without the corpus') without adding new semantic value beyond what is already in the input schema.
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 performs a baseline-vs-augmented counterfactual measurement, answering a question twice and reporting the delta and verdict. This is a specific verb-resource combination that distinguishes it from siblings like omnarai_query.
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 usage context (async job, ~35s, poll with omnarai_job) but does not explicitly state when to use this tool versus alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: context for bounded retrieval, council for live panel, divergence for reading existing records, info for meta-data, inquiry_brief for converting drafts, job for polling async tasks, query for async queries, and trace for counterfactual analysis. No overlap.
All tools follow a consistent 'omnarai_<noun>' pattern in snake_case (context, council, divergence, info, inquiry_brief, job, query, trace). No mixed styles or irregular verbs.
8 tools is well-scoped for a knowledge retrieval and deliberation system. It covers retrieval, live panel, divergence records, meta-info, inbox brief generation, async job polling, query execution, and tracing without unnecessary redundancy.
The tool surface covers core workflows: retrieval, deliberation, async job management, and meta-information. The only minor gap is the absence of tools for modifying or updating corpus data, but this aligns with the server's apparent read-only nature. Comprehensive for its stated purpose.