Blossom Research

Summarize the patent catalogue

aggregate_patents

Read-onlyIdempotent

Group-by count of patent families across one or two axes. Single axis: set groupByPrimary to 'compound' | 'compoundClass' | 'topic' | 'owner' | 'patentType' | 'office' | 'stage' | 'priorityYear'. Two axes: also set groupBySecondary (e.g. groupByPrimary='compoundClass', groupBySecondary='priorityYear'). Returns ranked buckets with sample citations; a 'priorityYear' axis is ordered by year. A family with two compounds is in two buckets. withoutPrimaryValue is the number of matching families with no value on the primary axis (no linked owner, no compound, no priority date): disclose it when it is large. The 'owner' axis counts only owners that are linked to a Blossom organisation record. Same filter shape as search_patents; filters are optional.

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_patents"
  }
}

Input Schema

Name	Required	Description
`filters`	Yes	Same filter shape as search_patents, except publicationNumbers and orderBy. Filters are OPTIONAL for aggregates: pass `{}` to group across all patent families.
`groupByPrimary`	Yes	Primary axis ("compound" \| "compoundClass" \| "topic" \| "owner" \| "patentType" \| "office" \| "stage" \| "priorityYear"). Required. "owner" counts only owners that are linked to a Blossom organisation record.
`groupBySecondary`	No	Optional second axis for a 2D matrix (e.g. "compoundClass" with "priorityYear", or "owner" with "compound"). The result has rowKey/colKey/count cells and stops at 50 buckets.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already cover read-only/idempotent/non-destructive, so the bar is lower, yet the description adds real behavioral detail: ranked buckets with sample citations, year-ordering for the priorityYear axis, the many-to-many double-count risk ('a family with two compounds is in two buckets'), and the owner-linkage limitation. Missing only rate/size limits and what 'sample citations' look like.

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?

Front-loads the operation, then axes, then return shape, then caveats – a logical order with little waste. Slight duplication in re-listing the groupByPrimary enum values that the schema already enumerates.

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?

With an output schema present the description needn't document return fields, yet it still explains bucket ordering, the 50-bucket cap context, and the unclassified 'withoutPrimaryValue' count. The main omission is the relationship to count_patents, which matters for a toolbox this dense.

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

Parameters3/5

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

Schema coverage is 100% and each parameter is documented in-schema, so baseline 3 applies. The description restates the groupByPrimary enum and adds only the 'priorityYear ordered by year' note and the owner-linkage restriction, which the schema already states.

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 ('Group-by count of patent families') plus the single- vs two-axis scope, which no sibling does. An agent can distinguish it from search_patents and count_patents from the first sentence alone.

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

Usage Guidelines3/5

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

Gives clear in-tool guidance (how to do a 2D matrix, that filters are optional, when to disclose withoutPrimaryValue), but never says when to pick this over the very close sibling count_patents, nor when a plain search is preferable. Usage is implied rather than contrasted with alternatives.

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?