Skip to main content
Glama
Sign In

Lune Research

by com.luneresearch
OverviewDiscussionsAdmin

Search related papers

search_related_papers
Read-onlyIdempotent

Given a paper_id, return the most semantically similar papers by embedding distance, NOT by citation links. Use for “more papers like this one” / “adjacent work on the same topic”. For papers this one cites or that cite it, use get_paper_citations instead. Each hit carries metadata, abstract, the closest non-abstract matched chunk as contexts, and a similarity score (0..1, higher is nearer). Returns up to limit papers; an unknown paper_id is an error, an empty list means no neighbors were found.

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": {
      "paper_id": "<paper_id>"
    },
    "name": "search_related_papers"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
paper_idYesA corpus paper UUID (from a paper search) to find neighbors for.

Output Schema

NameRequiredDescriptionDefault
papersYesSemantically nearest papers by embedding distance (NOT citation links), ordered nearest-first; empty when none were found.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds behavior the annotations cannot: ranking is by embedding distance rather than citations, each hit includes metadata, abstract, the closest non-abstract matched chunk as `contexts`, and a 0..1 `similarity`, plus failure semantics (unknown paper_id is an error, empty list means no neighbors).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core mechanism in the first clause, then the usage triggers, then the alternative, then the return shape and edge cases. Four sentences, each carrying distinct information; nothing is restated from the name or annotations.

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?

Despite an output schema existing (so return values need not be spelled out), the description still tells the agent what a hit contains and how to interpret `similarity` and empty results. For a 2-parameter read tool with full annotation coverage, nothing an agent needs to select or invoke it correctly is missing.

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?

Schema coverage is only 50%: `paper_id` is documented in the schema, but `limit` has no schema description beyond default 6 / max 20. The description compensates by stating 'Returns up to `limit` papers', giving the parameter meaning as a result cap rather than a filter. It stops short of noting the default or ceiling, so it improves on the schema without fully covering the gap.

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 and resource (return semantically similar papers for a paper_id) and immediately disambiguates the mechanism: embedding distance, explicitly 'NOT by citation links'. That contrast is what separates it from the citation sibling in a way an agent can act on without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives positive triggers ('more papers like this one' / 'adjacent work on the same topic') and an explicit exclusion with the named alternative: for citing/cited papers use `get_paper_citations`. This is the when-to-use / when-not-to-use / alternative pattern at full strength.

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

All Lune Research toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources