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

science-ai-mcp-server

by SelfPy

Recommend Target Journals

recommend_journals

Recommends ranked target journals for a paper from its title and abstract, with match grades and venue details to help authors compare candidates before submitting.

Instructions

Recommend ranked target journals for a paper from a 17,500-venue index. Each result includes a letter grade (A-F), a match percentage, tier (1-3), Scimago quartile, publisher, access (open, hybrid or subscription), OpenAlex 2-year mean citedness (an open proxy, not the Journal Impact Factor), a predatory-journal flag, responding times where the venue reports them, and up to 2 similar papers from the venue that our library holds. Runs on FTS5 + topic profiles, no LLM call. Costs 15 Science AI Journal credits per call, charged to the API key's account; an account without enough credits gets HTTP 402 and is not charged, and a call that matches no journal is refunded. The list is a ranked shortlist of candidates to check against each journal's aims and scope, not a prediction of acceptance: present it that way. Calls are rate-limited per API key; a refused call (401, 402, 403, 422, 429) is not charged and the error says what to do. If the server answers that this tool is not available through MCP yet, nothing was charged: use the Journal Finder in the web app at scienceaijournal.com/journal-recommender instead. Use when the user asks 'where should I submit this paper' or wants to compare target venues before deciding.

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": {
      "title": "<title>",
      "abstract": "<abstract>"
    },
    "name": "recommend_journals"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoSort mode. "best" (default) maximises relevance; "fastest" orders by responding time (earliest reported stage, shortest first, unknowns last); "mostAccepting" by publisher-stated acceptance rate; "highestIf"/"citednessHi" by 2-year mean citedness; plus SJR/quartile/h-index/recency/OA/index-membership orders.
fieldNoDetected research field for a topical boost (optional).
titleYesPaper title (required unless booleanQuery is supplied).
filtersNoOptional filter object. excludePredatory drops Beall's-archive matches; openAccessOnly keeps only OA journals; minTier sets a Tier 1/2/3 floor; respondingTimeOnly/maxRespondingDays gate on journal turnaround data.
abstractYesPaper abstract (required, can be empty string).
fullTextNoOptional full manuscript text for higher-signal matching.
keywordsNoOptional author keywords; comma-separated. High-signal topic input.
maxResultsNoHow many recommendations to return. Default 10, cap 25.
booleanQueryNoOptional Elicit-style Boolean query (Phase 0 / J0). Example: `("angle rigidity" OR "3D localization") AND wireless`. When supplied, bypasses bag-of-words token extraction and feeds the lowered FTS5 string directly. Parse failures return HTTP 400 with the character position of the error.
acknowledgeLowEnglishNoThe journal index is English-language: a text that does not look like English is refused with HTTP 422 and not charged. Set to true to run it anyway (charged as usual; expect rough matches).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv0.1.4
    • addedInput schema / properties / acknowledgeLowEnglish
      Added value: +{
      +  "description": "The journal index is English-language: a text that does not look like English is refused with HTTP 422 and not charged. Set to true to run it anyway (charged as usual; expect rough matches).",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / booleanQuery
      Added value: +{
      +  "description": "Optional Elicit-style Boolean query (Phase 0 / J0). Example: `(\"angle rigidity\" OR \"3D localization\") AND wireless`. When supplied, bypasses bag-of-words token extraction and feeds the lowered FTS5 string directly. Parse failures return HTTP 400 with the character position of the error.",
      +  "maxLength": 2000,
      +  "type": "string"
      +}
    • changedInput schema / properties / filters / description
      Previous value: -"Optional filter object. excludePredatory drops Beall's-archive matches; openAccessOnly keeps only OA journals; minTier sets a Tier 1/2/3 floor."New value: +"Optional filter object. excludePredatory drops Beall's-archive matches; openAccessOnly keeps only OA journals; minTier sets a Tier 1/2/3 floor; respondingTimeOnly/maxRespondingDays gate on journal turnaround data."
    • addedInput schema / properties / filters / properties / maxRespondingDays
      Added value: +{
      +  "description": "Keep only venues whose canonical responding time (earliest reported stage: first decision → acceptance → publication) is ≤ N days.",
      +  "maximum": 1095,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / filters / properties / respondingTimeOnly
      Added value: +{
      +  "description": "Keep only venues with a known responding-time metric (any stage).",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / sort / description
      Previous value: -"Sort mode. \"best\" (default) maximises relevance; \"fastest\" prefers fast-decision venues; \"highestIf\" sorts by 2-year mean citedness; \"mostAccepting\" prefers higher published-volume venues."New value: +"Sort mode. \"best\" (default) maximises relevance; \"fastest\" orders by responding time (earliest reported stage, shortest first, unknowns last); \"mostAccepting\" by publisher-stated acceptance rate; \"highestIf\"/\"citednessHi\" by 2-year mean citedness; plus SJR/quartile/h-index/recency/OA/index-membership orders."
    • changedInput schema / properties / sort / enum
      Previous value: -[
      -  "best",
      -  "fastest",
      -  "highestIf",
      -  "mostAccepting"
      -]New value: +[
      +  "best",
      +  "byTier",
      +  "sjrHi",
      +  "sjrLo",
      +  "quartileHi",
      +  "quartileLo",
      +  "citednessHi",
      +  "citednessLo",
      +  "hIndex",
      +  "az",
      +  "recent",
      +  "oaFirst",
      +  "byIndex",
      +  "highestIf",
      +  "fastest",
      +  "mostAccepting"
      +]
    • changedInput schema / properties / title / description
      Previous value: -"Paper title (required)."New value: +"Paper title (required unless booleanQuery is supplied)."
  2. First observedv0.1.3

TDQS

A4.4/5.0
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: 15 credits per call, HTTP 402 for insufficient credits with no charge, refund on zero-match, per-key rate limits, and the specific set of error codes (401/402/403/422/429) that are not charged. It additionally discloses the matching engine (FTS5 + topic profiles, no LLM call) and the unaffected fallback behavior when the tool reports itself unavailable — unusually rich for a no-annotation tool.

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?

Front-loaded correctly: purpose and index scope come first, then result shape, then cost/error behavior, then usage triggers. The result-field enumeration is dense and runs long in a single block — brackets or bullets would scan better — but nearly every clause carries decision-relevant information, including the citedness-vs-JIF caveat.

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 describes the returned fields, so an agent knows what it will get back. For a 10-parameter, credit-charging tool it also covers cost, refunds, failure modes, and the unavailable-via-MCP escape hatch — nothing material is missing.

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 description coverage is 100%, including the sort enum and nested filter object, so the schema already documents all ten parameters. The description adds no parameter-level detail beyond that (it never explains title/abstract/keywords weighting or how acknowledgeLowEnglish interacts with the 422 refusal), so the baseline 3 applies.

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?

Opens with a specific verb and resource — 'Recommend ranked target journals for a paper' — and scopes it to a '17,500-venue index.' It also enumerates what each result carries (letter grade, match %, tier, quartile, citedness proxy, predatory flag, similar papers), which makes the output unmistakable and separates it from siblings like ai_review_paper or find_research_gaps.

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?

Gives an explicit trigger ('where should I submit this paper' or comparing target venues before deciding) and pairs it with presentation guidance ('ranked shortlist of candidates... not a prediction of acceptance: present it that way'). It also supplies an alternative path when the tool is unavailable via MCP (web Journal Finder). No explicit when-not-to-use case is stated, so it falls short of a 5.

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