Skip to main content
Glama

Search Lacuna

search_lacuna
Read-onlyIdempotent

Find papers, authors, venues, institutions, research directions, hypotheses, and linked code, datasets, or models across the Lacuna ML/AI corpus, then route results to detail tools.

Instructions

Search Lacuna's ML/AI corpus for papers, research directions, authors, venues, institutions, novel research hypotheses, and research resources (code repositories, datasets, models, and demos linked to papers).

Start here for any question without an ID. Set search_type to what the question is about: paper for literature; cluster for a research direction ("who works on X", "what is the state of X"); author, institution or venue for a person, a lab or a conference; hypothesis for open research ideas; resource for code, datasets and models. Then pass a result's id or url to the matching detail tool.

A query that is an arXiv ID, a DOI, or an arXiv, DOI or OpenReview URL returns that exact paper. Paper results carry identifiers (arXiv ID, DOI, OpenReview URL where known), which other research tools accept.

For novel ML/AI research ideas, use search_type="hypothesis", then get_hypothesis on promising results.

search_type accepts all, cluster, paper, author, institution, venue, hypothesis, or resource. Use paper for literature and get_paper to read a result. Use other sources for biographies, news, and non-research web content.

Resources: search_type="resource" searches GitHub repositories, Hugging Face datasets/models, and Zenodo records that Lacuna has linked to at least one paper. To find benchmark or evaluation datasets, use search_type="resource" with resource_kind="dataset" (for example query "image classification benchmark" or a dataset name like "ImageNet"). resource_kind accepts codebase, dataset, model, or demo (one value or a list); provider accepts github, huggingface, or zenodo. Both filters require search_type "resource" or "all" (with either filter set, only resources are returned). Each result has an external url, a Lacuna context_url, and linked_paper_count; call get_resource on its id to list the linked papers (with their relationship to the resource), then get_paper on those papers for reported results and numbers. Resource search does not support date_from/date_to, venue, year sorting, or semantic ranking.

ranking_profile accepts:

  • default / lexical (default): production ranking; relevance-sorted paper searches combine lexical and semantic retrieval when fields is unset.

  • semantic: conceptual paper retrieval; supported for paper and all.

  • bm25_title_abstract / bm25: lexical paper matching over those fields.

sort accepts relevance (default), year_desc, or year_asc. Semantic ranking cannot use year sorting; constrain recency with date_from/date_to instead. date_from and date_to are inclusive YYYY, YYYY-MM, or YYYY-MM-DD bounds. author_id_or_url constrains a paper search to one author. Pass an author ID or Lacuna author page URL; it requires search_type="paper".

fields optionally restricts and weights lexical fields, for example "title^4,abstract". Supported names are title, abstract, summary, concepts, name, top_names, and venue, plus description, topics, provider_key, and paper_titles for resources (a resource's title already includes its description, topics, README text, and linked paper titles). Fields must exist on the selected search_type, weights must be within 0 < weight <= 100, and fields cannot be combined with semantic ranking.

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": {
      "query": "<query>"
    },
    "name": "search_lacuna"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNorelevance
limitNo
queryYes
venueNo
fieldsNo
offsetNo
date_toNo
providerNo
date_fromNo
search_typeNoall
resource_kindNo
ranking_profileNo
author_id_or_urlNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.5.1
    • addedInput schema / properties / provider
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Provider"
      +}
    • addedInput schema / properties / resource_kind
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Resource Kind"
      +}
  2. Changed1 schema field changedv0.3.0
    • addedInput schema / properties / author_id_or_url
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Author Id Or Url"
      +}
  3. First observedv0.2.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), yet the description still adds substantial behavior: ID/DOI/URL queries resolve to one exact paper, resources are limited to those linked to at least one paper, and resource search silently ignores date_from/date_to, venue, year sorting, and semantic ranking. It also discloses result shape hints (external url, context_url, linked_paper_count) and filter coupling rules.

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 task-critical routing guidance is front-loaded in the first two sentences, and the later blocks are scannable parameter documentation. There is mild redundancy: search_type's allowed values are enumerated and then re-explained ("Use paper for literature and get_paper to read a result"), and the hypothesis recommendation appears twice.

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?

For a 13-parameter search tool with sibling detail tools, the description supplies the routing logic, the type taxonomy, and the constraint interactions an agent needs to call it correctly; the presence of an output schema means return values need not be described. The remaining gap is pagination behavior, since limit and offset appear nowhere in either the schema or the description.

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?

With 0% schema description coverage across 13 parameters, the description carries the full burden and covers most of the important ones: search_type values, resource_kind and provider values plus their search_type precondition, ranking_profile options and their compatibility constraints, sort values, date bound formats, author_id_or_url semantics, and the fields weighting syntax including 0 < weight <= 100. Only limit and offset go completely undocumented, so it stops short of full coverage.

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 opens with a specific verb and resource ("Search Lacuna's ML/AI corpus") and enumerates exactly what entity types are covered: papers, research directions, authors, venues, institutions, hypotheses, and resources. It also distinguishes itself from the detail siblings by pointing to get_paper, get_hypothesis, and get_resource for result IDs.

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?

It states an explicit entry condition ("Start here for any question without an ID") and then maps question intent to search_type values with concrete phrasing such as "who works on X" for cluster and "code, datasets and models" for resource. It also names when-not-to-use cases ("Use other sources for biographies, news, and non-research web content") and the follow-up path to detail tools.

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