Skip to main content
Glama
mp-juns

universal-research-mcp

by mp-juns
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

memory_search_candidates

Read-onlyIdempotent

Search research memory for provenance-bound candidate matches. Use these candidates to locate original evidence before drawing conclusions, ensuring claims are source-grounded and verifiable.

Instructions

Return provenance-bound candidates. Fetch original evidence before concluding.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoconfigured
queryYes
top_kNo
statusNo
candidate_backendNoconfigured

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.9.3
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "title": "memory_search_candidatesDictOutput",
-  "type": "object"
-}New value: +null
  2. Changed4 schema fields changedv0.7.0
    • addedInput schema / properties / candidate_backend
      Added value: +{
+  "default": "configured",
+  "enum": [
+    "configured",
+    "universal",
+    "event_first"
+  ],
+  "title": "Candidate Backend",
+  "type": "string"
+}
    • removedInput schema / properties / mode / const
      Removed value: -"lexical"
    • changedInput schema / properties / mode / default
      Previous value: -"lexical"New value: +"configured"
    • addedInput schema / properties / mode / enum
      Added value: +[
+  "configured",
+  "lexical",
+  "semantic",
+  "hybrid",
+  "adaptive"
+]
  3. Changed2 schema fields changedv0.3.0
    • addedInput schema / properties / mode / const
      Added value: +"lexical"
    • removedInput schema / properties / mode / enum
      Removed value: -[
-  "lexical",
-  "hybrid",
-  "semantic"
-]
  4. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the description only needs to add context beyond that. It does add that results are provenance-bound candidates and that they are not sufficient for conclusions. However, it does not disclose ranking behavior, empty-result handling, mode effects, or how candidates relate to original evidence.

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 two sentences with no filler. The first sentence states the core return behavior, and the second adds an actionable workflow warning. Every word earns its place, making it appropriately concise and front-loaded.

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

Completeness2/5

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

Given five parameters, two enums, no schema descriptions, and no output schema, the description is too sparse for reliable invocation. It does not explain what a 'candidate' contains, how modes differ, what status accepts, what candidate_backend controls, or how top_k behaves. The one useful workflow hint about fetching original evidence is insufficient for the tool's complexity.

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

Parameters1/5

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

Schema description coverage is 0%, and the description provides no information about the five parameters: query, mode, top_k, status, or candidate_backend. The phrase 'provenance-bound candidates' does not help an agent understand parameter meaning, required inputs, enums, or defaults. This is a significant gap.

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

Purpose4/5

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

The description clearly states the tool returns 'provenance-bound candidates', which is a specific verb and resource, and distinguishes it from evidence retrieval by instructing to 'Fetch original evidence before concluding'. It does not explicitly name a sibling tool, but the candidate-versus-evidence distinction makes the purpose understandable.

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 description provides a clear usage directive: after getting candidates, the agent should fetch original evidence before drawing conclusions. This implies the tool is for preliminary retrieval rather than final evidence. It does not explicitly state when to avoid the tool or name alternatives, but the workflow guidance is clear.

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

Deploy Server

Other Tools