Skip to main content
Glama
cholhwanjung

Claude Desktop Research MCP Server

by cholhwanjung

prune_paper_figures

Removes all figure files from a paper's figures directory except those specified in the 'keep' list, preserving only core architecture or result plots selected by caption analysis.

Instructions

vault의 papers/<slug>/figures/ 에서 keep에 명시된 파일만 남기고 나머지 삭제 (ADR-015, ADR-016).

LLM이 extract_paper_figures 결과의 caption을 보고 핵심 architecture / 결과 plot만 선별 → 선별 결과를 keep으로 넘겨 호출. 나머지 figure는 디스크에서 제거.

Args: paper_id: arXiv ID (정규화 검사용). keep: 남길 figure의 파일 식별자 리스트. "figures/fig_1.png" 또는 "fig_1.png" 둘 다 허용. 빈 리스트면 모든 figure 삭제. slug: vault 디렉토리명 (title-slug). 비우면 arxiv_id 사용 (legacy 호환).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paper_idYes
keepYes
slugNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior3/5

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

No annotations are provided, so the description must carry the full burden. It states the tool deletes files (destructive action) but does not emphasize irreversibility or permission requirements. The behavioral context is adequate but could be stronger.

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 description is well-structured: a single-sentence summary followed by usage context, then parameter details. It is concise without wordiness, though the parameter list could be slightly shorter.

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?

Given the moderate complexity (3 params, one list) and presence of an output schema (not shown), the description covers the intended workflow and parameter behaviors. It lacks error handling or return value details but is sufficient for common use.

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

Parameters5/5

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

Schema coverage is 0%, but the description compensates thoroughly: explains 'paper_id' for normalization, 'keep' allows two formats and empty list means delete all, 'slug' falls back to arxiv_id for legacy compatibility. This adds significant meaning 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?

The description clearly states the tool prunes figures by deleting all except those in 'keep', specifying the directory path. It uses a specific verb and resource, and distinguishes from siblings like 'extract_paper_figures' and 'prune_paper_tables'.

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 context: the tool is intended to be called after 'extract_paper_figures' with a selected list of figures. It references ADR-015/016 for context. However, it lacks explicit when-not-to-use guidance compared to alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cholhwanjung/research-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server