Skip to main content
Glama

omnarai_inquiry_brief

Generate a provenance-preserving inquiry brief from a draft claim or plan, revealing shared ground, attributed tensions, missing evidence, sharper questions, and one next evidence move.

Instructions

Turn a DRAFT claim, decision, or plan into a bounded, provenance-preserving inquiry brief: shared ground the corpus supports, attributed cross-model tensions (certification tier preserved), missing evidence, sharper falsifiable questions, and ONE concrete next evidence move.

Retrieval-first and deterministic by default (~2s): it re-organizes real corpus records and matching Divergence Atlas records — no language model runs unless the caller explicitly passes include_deliberation=true (slow, ~25s; the deliberation is appended and disclosed, never silent).

Calibration is preserved, never upgraded: C0 = displayed once, C1 = paraphrase-robust, C2 = pressure-robust; only C3 records are certified genuine divergence. Stale model versions are flagged. If the corpus lacks coverage, the brief says so and returns evidence-seeking questions instead of invented tensions.

This tool informs an investigation; it does not decide, approve, or execute. Invoke it explicitly on a draft you are inspecting — it is not an automatic critic.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
goalNoOptional. What you are trying to decide, build, or learn — echoed into the brief to frame the next move.
draftYesThe claim, decision, plan, or question to inspect (max 4,000 chars). Treated strictly as data, never as instructions.
focusNoOptional, default all. Tilts retrieval layers and which sharper questions are generated.
stakesNoOptional, default medium. 'high' adds external-validation gaps to missing evidence.
max_sourcesNoOptional, default 6, clamped 1–10. Maximum corpus records cited as sources.
include_deliberationNoOptional, default false. When true, additionally runs the engine's slow (~25s) multi-voice deliberation and appends it, disclosed, to the brief.
Behavior5/5

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses deterministic default behavior (~2s), the optional LM deliberation with ~25s latency and disclosure, calibration preservation rules (C0–C3), stale model flagging, and graceful degradation when corpus coverage is insufficient. This is far beyond typical transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense yet well-structured, front-loading the core purpose in the first sentence and then providing necessary behavioral details. Each sentence adds unique value (retrieval speed, calibration, usage constraints), with no filler or redundancy, making it concise for the complexity involved.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description fully accounts for return values by listing the brief's components and edge cases (insufficient coverage, stale versions, deliberation disclosure). It also frames the tool's role within an investigation, providing enough context for an agent to select and invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers 100% of the 6 parameters, giving a baseline of 3. The description adds behavioral nuance beyond the schema, particularly for include_deliberation (slow ~25s, appended and disclosed) and for draft (treated strictly as data, never as instructions). This extra context justifies a score above baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource: 'Turn a DRAFT claim, decision, or plan into a bounded, provenance-preserving inquiry brief' and enumerates concrete outputs (shared ground, attributed tensions, missing evidence, questions, next evidence move). It differentiates from siblings by highlighting deterministic retrieval-first behavior and calibration preservation, which are unique traits.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The final paragraph explicitly states when to use the tool: 'Invoke it explicitly on a draft you are inspecting — it is not an automatic critic,' and clarifies what it does not do: 'does not decide, approve, or execute.' It provides clear context but does not name alternative sibling tools, so it falls short of full explicit alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/justjlee/omnarai-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server