knowledge-engine

Overview Schema Source Related Servers Discussions Admin

research

Answer AI-engineering decision questions with grounded, current, cited evidence from the knowledge base and live web searches, tracing each claim to its source.

Instructions

Answer a decision question with grounded, current, cited evidence.

Runs the full loop: searches the knowledge base, runs live web searches, fetches the top pages, and synthesizes a dated answer with DeepSeek-V3. Every claim is traced to a retrieved source.

CHECK THE SDK FIRST — do NOT reach for this before checking whether the SDK already ships the primitive you need. The default authority for "how do I build this" is the SDK's own documented pattern (LangGraph via the docs-langchain MCP; Vercel AI SDK / OpenAI / Google via Context7) — most 2026 agent work is a solved, established pattern. Consult this tool ONLY when the established SDK pattern is insufficient or absent, or when you are tuning / choosing between mature options and need current field evidence. This KB is biased toward the research frontier by construction; letting it drive a decision the SDK already answers leads to reinventing wheels the SDK ships.

SCOPE — the fast-moving AI-engineering frontier (agents, LLMs, harnesses, evals, agent security, AI coding tools, model capability/cost trends), where current reality outruns your training. It is NOT for general/evergreen software architecture (CRM, omnichannel, helpdesk, classical patterns — you already know those) or library/API docs (use Context7). Sources discovered here are promoted back into the KB, so keeping questions on-frontier keeps the KB clean.

Returns JSON: {answer, citations: [{url,title,date}], confidence, retrieval_date, kb_coverage, warnings, sources_used}. Check warnings and confidence before trusting the answer.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`question`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 17, 2026

TDQS

A4.8/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses the internal workflow (search, fetch, synthesize with DeepSeek-V3), the side effect of promoting sources back into the KB, and the return envelope with warnings/confidence. This goes well beyond a generic 'research' label.

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

Conciseness4/5

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

The description is long but deliberately structured in labeled sections (default authority, scope, returns), and each section carries actionable guidance that would be hard to compress further without losing value. It is front-loaded with the core purpose before diving into usage nuances.

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?

For a single-parameter tool with no annotations, the description covers purpose, scope, exclusions, alternatives, workflow, output fields, and trust caveats. The output schema is described as a JSON object with citations, confidence, warnings, and retrieval_date, so the agent has everything needed to invoke and interpret the tool 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 schema provides only the parameter name 'question' with 0% description coverage. The description compensates by clarifying what qualifies as a question (a decision question on the frontier) and what is out of scope, which helps the agent frame the input even though it doesn't restate the parameter format verbatim.

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 states a specific verb and resource: 'Answer a decision question with grounded, current, cited evidence.' It also differentiates itself from the sibling query_knowledge by explicitly describing the full loop (searches KB, live web searches, fetches pages, synthesizes) rather than a simple KB lookup.

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

Usage Guidelines5/5

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

The description gives explicit when-to-use and when-not-to-use guidance: 'CHECK THE SDK FIRST — do NOT reach for this before checking whether the SDK already ships the primitive you need.' It names alternatives (docs-langchain MCP, Context7) and defines the scope boundary (frontier AI engineering vs general software architecture and docs).

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

Deploy Server