celiums-memory

research_synthesize

Hybrid search and synthesize top-K results into a citation-bearing analysis. Distinguishes well-supported claims from unsupported ones using a frontier LLM. Logs query to project session.

Instructions

Run a hybrid search and synthesize the top-K results into a careful, citation-bearing analysis using a frontier LLM (Opus 4.7 by default). Output explicitly distinguishes well-supported claims from claims it cannot back up with the retrieved evidence. Logs the query into the project session log.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "projectId": "<projectId>",
      "query": "<query>"
    },
    "name": "research_synthesize"
  }
}

Input Schema

Name	Required	Description
`projectId`	Yes
`query`	Yes	The research question for this synthesis pass.
`topK`	No	How many docs to feed to the LLM. Default 10, max 30.
`model`	No	Override LLM model for this call. Defaults to CELIUMS_LLM_MODEL.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.2.5Apr 28, 2026

TDQS

A4/5.0

Behavior4/5

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

Given no annotations, the description provides good behavioral detail: uses Opus 4.7 by default, logs query, distinguishes supported claims. Missing potential side effects like cost or rate limits, but otherwise transparent.

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?

Three focused sentences with front-loaded main action. No unnecessary words. Efficiently communicates core behavior and key features.

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

Completeness4/5

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

Covers main behavior, logging, and output distinction. Without output schema, the description adequately implies the return type is an analysis text. Could add error handling or time limits, but sufficient for most agents.

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

Parameters3/5

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

The schema already covers 75% of parameters with descriptions. The description adds little beyond schema; for 'query' it says 'research question', which is similar to schema. Baseline 3 is appropriate.

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 clearly states the tool performs hybrid search and synthesis with citations, distinguishing it from siblings like research_search. The verb 'synthesize' and specific output details make the purpose unambiguous.

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

Usage Guidelines3/5

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

The description implies when to use (for a synthesis analysis), but does not explicitly contrast with alternatives like research_search or other tools. No guidance on when not to use or prerequisites.

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