Skip to main content
Glama

Find research papers

search_papers
Read-onlyIdempotent

Search Blossom's papers (peer-reviewed studies, meta-analyses, reviews). For a known DOI, pass the standalone DOI or doi.org URL in query for exact lookup; a miss stays empty and all other filters still apply. searchMatch shows lexical matching fields, not verified relevance: when titleOrSummaryMatch is false, the match is in supporting context and may be incidental or about another jurisdiction. Read that context, distinguish direct evidence from background comparisons, and do not treat acronym matches as proof of a named programme. Use linkedTrialRegistrationNumbers with exact ClinicalTrials.gov IDs to follow curated relatedTrials links from trials to papers. Registry-ID lookup reserves at least one bounded result slot per requested ID, returns matchedTrialRegistrationNumbers on each paper, and prioritizes papers structurally labelled primary (verified labels first), so an ID absent from matchedTrialRegistrationNumbers across the returned results has complete no-link coverage when no other paper filters were passed. paperRole is authoritative only when paperRoleVerified is true; otherwise report the label as unverified. Use accessTypes with canonical values 'open' or 'paywall' for access-status questions. Use orderBy:'relevantInfluential' only after the user confirms a subject axis for influential-literature discovery: it restricts results to the primary title-or-summary subject cohort, then ranks that cohort by citation count. Never use it to imply that a paper is verified as related to an unresolved citation. Set retrievalMode:'hybrid' only for natural-language discovery questions, lexical for names and exact identifiers. Hybrid candidates carry retrievalMatch ranks, which are not verified relevance or an exhaustive count. When retrievalMatch is absent, these are lexical-only results, including when hybrid is disabled or unavailable; do not describe them as found by meaning. Use to LIST papers matching filters. For 'how many?' questions use count_papers instead.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_papers"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryNo
dateToNo
topicsNoTopic slugs (e.g. "depressive-disorders", "ocd"). Common abbreviations like "PTSD", "TRD", "OCD" and short names like "depression", "anxiety" are auto-mapped to canonical slugs.
orderByNoSort order. "relevance" = best text match (default), "date" = newest first; use date for "latest"/"recent"/"new" questions. "citations" = most-cited first. "relevantInfluential" = citation-ranked papers that first qualify by the primary title-or-summary subject pattern; use only after the user confirms a subject axis for influential-literature discovery.relevance
dateFromNo
compoundsNoCompound slugs (e.g. "psilocybin", "mdma"). Street names ("shrooms", "ecstasy") and brand/program names ("COMP360", "MM-120") are auto-mapped.
accessTypesNoCanonical paper access status. Use ["open"] for open-access papers or ["paywall"] for paywalled / subscription-only papers.
authorSlugsNo
journalSlugNo
studyDesignNo"meta" = meta-analyses/reviews; "individual" = primary studies
retrievalModeNoUse hybrid only for natural-language discovery questions; lexical for names, identifiers, exact titles and counts. Hybrid is bounded candidate retrieval, not proof of relevance or exhaustive coverage.
linkedTrialSlugsNoSlugs of trials this paper is linked to (relatedTrials[]). Use to find papers from a specific trial.
outcomeMeasureSlugsNoSlugs of clinical / mental-health rating scales used as outcome measures (e.g. "beck-depression-inventory", "madrs", "y-bocs"). Common abbreviations like "BDI", "MADRS", "PHQ-9", "GAD-7", "Y-BOCS", "PCL-5", "MEQ-30" are auto-mapped.
linkedTrialRegistrationNumbersNoExact ClinicalTrials.gov IDs of trials linked through curated relatedTrials references (for example NCT03537014).

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses real behavior: a DOI miss returns empty while other filters still apply, registry-ID lookups reserve a bounded slot per ID and return matchedTrialRegistrationNumbers so absence implies complete no-link coverage, and missing retrievalMatch means lexical-only results. It also flags which output labels are authoritative (paperRole only when paperRoleVerified is true).

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

Conciseness3/5

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

One dense unbroken paragraph of roughly 300 words with no visual structure; guidance on hybrid retrieval and relevantInfluential partly repeats the schema's own parameter descriptions. It is front-loaded with purpose and free of filler, but the volume makes it hard to scan at invocation time.

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 15-parameter, read-only tool with an output schema and annotations, the description covers the semantically hard parts (matched vs incidental context, retrieval provenance, trial-link coverage) that an agent could otherwise misreport. The remaining omission is minor: no mention of pagination/limit behavior despite a hard maximum of 20.

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?

At 60% schema coverage with 15 parameters, the description carries real weight: it defines the DOI form for query, the canonical 'open'/'paywall' values for accessTypes, the exact NCT pattern use for linkedTrialRegistrationNumbers, and the restriction semantics of relevantInfluential. Undocumented parameters (limit, dateFrom/dateTo, authorSlugs, journalSlug, linkedTrialSlugs, studyDesign) are left to self-evident names, so it stops short of full compensation.

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?

"Search Blossom's papers (peer-reviewed studies, meta-analyses, reviews)" gives a specific verb, resource, and content scope, and the closing line routes "how many?" questions to count_papers instead. An agent can separate this from get_paper, count_papers, and aggregate_papers without opening any 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?

The description states when to use exact DOI lookup in query, when to choose hybrid vs lexical retrievalMode, when orderBy:'relevantInfluential' is permitted, how to use linkedTrialRegistrationNumbers, and explicitly defers counting to count_papers. Alternatives and preconditions are named rather than implied.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources