Skip to main content
Glama
Native Research MCP

Native Research MCP

by pipiwego

research_evidence

Read-onlyIdempotent

Retrieve saved research evidence by ID without contacting a provider; returns model-extracted findings rather than raw page content.

Instructions

Read saved evidence by ID without a provider request. Evidence contains model extractions, not raw page bytes.

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": {
      "research_id": "<research_id>"
    },
    "name": "research_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
research_idYes
evidence_idsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still earns credit by disclosing two behaviors not in the annotations: no provider/network request is made, and the returned evidence is model-extracted content rather than raw page bytes, which directly affects how an agent should treat results.

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?

Two short sentences, front-loaded with the action and immediately followed by the most decision-relevant caveat about return content. No filler or repetition of the tool name.

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

Completeness3/5

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

The absence of an output schema makes the note about extraction-vs-raw-bytes valuable, and the no-provider-request claim is useful context. Still, with 0% parameter documentation and an optional list parameter whose default behavior is unstated, an agent cannot fully predict what a call returns for a given input.

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

Parameters2/5

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

Schema description coverage is 0%, so the description carries the full burden, yet it only vaguely implies the 'by ID' lookup. It never explains the required research_id versus the optional evidence_ids list, nor what happens when evidence_ids is null (all evidence for the research, presumably). This is a significant gap for a 2-parameter tool with no schema documentation.

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?

States a specific verb and resource ('Read saved evidence by ID') and adds a distinguishing qualifier ('without a provider request'), which separates it from provider-backed siblings like deepseek_read_url. It does not name an alternative directly, but the scope is 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 phrase 'without a provider request' implies the tool is the cheap cached path to use when evidence IDs are already known, and the mention of model extractions hints at when it is insufficient (raw page bytes). However, there is no explicit statement of when to use it versus research_recover or research_status, so usage is inferred rather than stated.

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