Blossom Research

Summarize the paper catalogue

aggregate_papers

Read-onlyIdempotent

Group-by count of papers across one or two axes. Single axis: set groupByPrimary to 'compound' | 'topic' | 'journal' | 'year' | 'studyDesign'. Two axes: also set groupBySecondary (e.g. groupByPrimary='compound', groupBySecondary='year') for a 2D matrix — perfect for 'how research per compound has evolved over time'. Returns ranked buckets with sample citations. 1D buckets: {key, label, count, sample}. 2D buckets: {rowKey, rowLabel, colKey, colLabel, count, sample}. Same supported filter shape as search_papers, including accessTypes; filters are optional. Paper aggregates use the primary query pattern only; ordinary search_papers may relax after a miss. With relevantInfluential, title-or-summary eligibility matches search/count. When hitCap is true, disclose that bucket counts cover only matchedFetched of total papers and are not exhaustive.

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": {
      "filters": "<filters>",
      "groupByPrimary": "<groupByPrimary>"
    },
    "name": "aggregate_papers"
  }
}

Input Schema

Name	Required	Description
`filters`	Yes	Same supported filter shape as search_papers, except linkedTrialRegistrationNumbers. Filters are OPTIONAL for aggregates — pass `{}` to group across all papers. `limit` is ignored.
`groupByPrimary`	Yes	Primary axis to group by ("compound" \| "topic" \| "journal" \| "year" \| "studyDesign"). Required.
`groupBySecondary`	No	Optional second axis for a 2D matrix (e.g. "compound × year"). Result has rowKey/colKey/count cells; caps at 50 buckets after sort.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare the read-only, idempotent, non-destructive profile, so the description focuses on behavior beyond that: it states the shape of returned buckets, the ranking, and the crucial hitCap caveat that bucket counts may cover only matchedFetched of total papers. The only gap is that it doesn't restate the 50-bucket cap in prose (it lives in the schema) or describe performance/cost characteristics.

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 front-loaded with the core operation and then layers axis guidance, examples, and return shape in a logical order with no filler sentences. A few clauses are terse to the point of being cryptic, notably 'Paper aggregates use the primary query pattern only; ordinary search_papers may relax after a miss.'

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?

With an output schema present and full schema coverage, the description only needs to cover intent, axis selection, and behavioral caveats, all of which it does. The hitCap disclosure and the 2D matrix explanation cover the non-obvious risks an agent would otherwise miss.

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 100%, so the baseline is 3; the description earns an extra point by mapping intent to parameter combinations, e.g. groupByPrimary='compound' with groupBySecondary='year' for a time-evolution query, and by explaining the 1D vs 2D bucket key names. It adds interpretation rather than merely repeating the enums.

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 names a specific operation (group-by count of papers) and enumerates the exact axes available, so the agent knows precisely what the tool produces. It differentiates itself from siblings like count_papers and search_papers by describing grouped, ranked bucket output rather than flat counts or result lists.

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?

It clearly explains the single-axis versus two-axis usage pattern and supplies a concrete motivating example ('how research per compound has evolved over time'), plus a note that filters are optional. It also constrains relevantInfluential to a post-confirmation scenario. It never explicitly contrasts with the sibling count_papers, so the when-not guidance is incomplete.

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

All Blossom Research tools Inspect

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

Need Help?