Skip to main content
Glama

ResearchShelf

research_shelf
Destructive

Track and manage research papers gathered during browsing: list, confirm, score, remove, and export citations in BibTeX, RIS, or JSON.

Instructions

Manage the research shelf — an in-memory tracker for papers inspected during research.

Papers are automatically added when the following tools resolve a paper, RFC, or citable repository: arxiv, semantic_scholar, ietf, github (for repos with CITATION.cff), and web_fetch_incisive (via its DOI fast path). Use this tool to review, score, confirm, or remove tracked entries, and to export citations in BibTeX, RIS, or JSON format.

Actions: list, confirm, remove, score, note, export, import, clear.

Query formats:

  • list: section name (active, retracted, all) — default active

  • confirm/note: DOI of the paper (note takes DOI + space + note text)

  • remove: comma-separated DOIs

  • score: DOI + space + integer (e.g. "10.1234/foo 8")

  • export: format name (bibtex, ris, json), optionally "with_retracted" (e.g. "bibtex with_retracted")

  • import: JSON export string (merges with current shelf)

  • clear: ignored

The shelf survives context compaction within the same session. For cross-session persistence, use export json to save the shelf to a memory file, then import it in a future session.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryNoFor confirm/score/note: the DOI of the paper. For remove: comma-separated DOIs to remove. For score: DOI followed by space and integer value (e.g. '10.1234/foo 8'). For note: DOI followed by space and note text. For list: section name (active, retracted, all) — default active. For export: format name (bibtex, ris, json), optionally followed by 'with_retracted' to include retracted entries (e.g. 'bibtex with_retracted'). For import: the JSON string to import. For clear: ignored (pass any value).
actionYesThe operation to perform. list: show all tracked papers. confirm: mark a paper as confirmed/useful. remove: batch remove papers by DOI (comma-separated). score: set an integer score for a paper. note: set a freetext note on a paper. export: export shelf in bibtex, ris, or json format. import: import shelf from a JSON export string. clear: remove all entries from the shelf.
Behavior5/5

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

Beyond the destructiveHint annotation, the description discloses in-memory storage, survival across context compaction, auto-add behavior, import merge semantics, and the cross-session export/import workflow. It also clarifies destructive actions like clear and remove.

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 opens with a clear one-sentence purpose and uses structured sections for actions and query formats. It is long, but the length is justified by eight distinct actions and their syntax; no content is filler, though some redundancy with the schema exists.

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 tool's complexity (8 actions, query formats, auto-population sources, persistence), the description covers all essential usage aspects. It does not describe return values or error behavior, but the detailed schema and annotations make it sufficient for correct selection and invocation.

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

Parameters4/5

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

The schema already covers both parameters at 100%, but the description adds a readable, example-driven query format list and the important detail that import merges with the current shelf, which is not in the schema's import description. This enhances usability beyond the structured fields.

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 this tool manages an in-memory research shelf for tracking papers, with specific verbs: review, score, confirm, remove, export. It distinguishes itself from source-fetching sibling tools by focusing on post-discovery management and listing the tools that auto-populate the shelf.

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 explains when to use this tool: after research tools like arxiv, semantic_scholar, ietf, github, or web_fetch_incisive have resolved papers. It gives clear context for managing tracked entries and cross-session persistence, though it does not explicitly state when not to use it or name direct 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/blightbow/parkour-mcp'

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