Skip to main content
Glama
science-ai-mcp-server

science-ai-mcp-server

by SelfPy

AI Multi-Agent Peer Review (single agent)

ai_review_paper

Run a specialist peer-review agent on manuscript text to get a structured editorial decision with score, verdict, strengths, concerns, and questions for authors.

Instructions

Run one specialist reviewer agent (methodology, formulas, originality, literature, reproducibility, clarity or figures) on a prepared agent prompt and return the structured editorial decision: score (1-10), verdict (Accept / Minor Revision / Major Revision / Reject), summary, strengths, concerns, detailed multi-section review, confidence band, and questions for the authors. Costs 4 Science AI Journal credits per call (one call = one agent), charged to the API key's account; an account without enough credits gets HTTP 402 and is not charged. For a whole manuscript, AI Review in the web app at scienceaijournal.com/ai-review runs all 9 specialist agents plus a synthesis in one pass.

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": {
      "prompt": "<prompt>"
    },
    "name": "ai_review_paper"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptYesPrepared agent prompt — usually the manuscript text plus any agent-specific framing. The server wraps it in <manuscript> tags to defuse injection, prepends RAG examples if agentType is supplied, and runs the chosen Claude model.
agentTypeNoWhich specialist reviewer to run. Selects the calibration examples drawn from real peer reviews for that reviewer; defaults to a generic reviewer when omitted. "plagiarism" is an alias for "originality".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.4

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it discloses a per-call cost of 4 credits charged to the API key's account, the exact failure mode (HTTP 402 when credits are insufficient, with no charge), and that the server wraps the prompt in <manuscript> tags to defuse injection. That is precisely the cost/error/auth context an agent needs before invoking a metered call.

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 core action, the return payload, the cost, and the multi-agent alternative each appear once and in a sensible order, with no filler. The first sentence is an overloaded run-on that stacks the full return-field list, which hurts scannability slightly but does not waste words.

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?

There is no output schema, yet the description fully enumerates the returned fields (score, verdict, summary, strengths, concerns, multi-section review, confidence band, author questions), so an agent knows what to expect. Combined with the cost and 402 behavior, nothing material is missing for a two-parameter metered call.

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?

Schema coverage is 100%, so the schema already documents both parameters, and the description's re-listing of agent types adds little beyond the enum. It also omits two enum values present in the schema ("language" and "plagiarism"), so the parameter text mildly under-describes the schema rather than extending it. Baseline 3 applies.

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 states a specific verb and resource — run one specialist reviewer agent on a prepared prompt — and enumerates the specialist roles plus the full structured return. It also contrasts itself with the multi-agent web flow ("one call = one agent"), though it never distinguishes itself from a sibling such as pre_check_paper, so it stops short of a 5.

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?

It makes clear this is the single-reviewer path and names the alternative for whole-manuscript review (the web app's 9 agents plus synthesis), which is the main routing decision an agent faces. It does not state exclusions relative to the sibling tools in this server, so it is clear context without full when-not guidance.

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