Skip to main content
Glama
Academic Polish MCP

Academic Polish MCP

by 212Yggg

polish_academic_text

Polishes Chinese or English academic paragraphs with light-to-deep editing, returning change notes and risk warnings while preserving citations, numbers, LaTeX formulas, URLs, DOIs, and key terms.

Instructions

润色用户提供的中英文论文段落,返回修改稿、修改说明和风险提示。默认检查常见数字、引文、LaTeX公式、URL、DOI及指定术语;检测到变化时保留原文。文本会发往服务端配置的模型API。不生成新事实或参考文献,不读写文献表。

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": {
      "text": "<text>"
    },
    "name": "polish_academic_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNolight fixes wording; standard improves clarity; deep may reorganize sentences; concise shortens.standard
textYesThe paragraph or short section to polish.
languageNoLanguage for editing notes. The source text keeps its original language; this tool does not translate.zh-CN
disciplineNoOptional discipline, such as computer science or education.
target_styleNoOptional style requirement, such as concise journal prose.
preserve_termsNoTerms that must remain exactly unchanged.
strict_preservationNoWhen true, reject a draft if detected citations, numbers, formulas, URLs, DOIs, or protected terms change; return the original text and warnings.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses the return payload, the default preservation checks (numbers, citations, LaTeX, URLs, DOIs, protected terms), the fallback of returning the original on detected change, and — importantly — that text is transmitted to a server-side model API. It still omits cost, latency, failure modes, and whether the operation has side effects beyond the API 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?

Three tight sentences with the action and return value front-loaded, followed by default behavior and then the negative scope. Dense but every clause earns its place; the only mild cost is that the privacy note sits mid-paragraph rather than being highlighted.

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?

Because there is no output schema and no annotations, the description must explain returns and safety — and it does, naming the three return components and the external API transmission. Complete enough to call correctly, with only operational details (length limits beyond the schema's 12000, latency, error behavior) left implicit.

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%, so all seven parameters including both enums are already documented, and the description largely restates that the default integrity checks cover numbers, citations, formulas, URLs, DOIs and protected terms. Baseline 3 applies; the description confirms the preserve_terms/strict_preservation defaults but adds little syntax or behavioral detail beyond the schema.

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?

States a specific verb+resource pair (polish academic paper paragraphs in Chinese or English) and names what comes back (revised draft, revision notes, risk warnings). An agent knows exactly what class of operation this is without opening the schema.

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?

Scope is explicit — input is a paragraph or short section, and the tool explicitly does not generate new facts or references and does not read or write bibliography tables. No alternatives are named (there are no siblings), so there is nothing further to route against, but there is also no guidance on when a paragraph is too long or when to prefer a non-AI edit.

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