Skip to main content
Glama

Compare project collections

compare_collections
Read-onlyIdempotent

Compare 2–4 projects or collections (id or code from list_collections) with identical research-item filters. Reports denominators, missingness, dates and top types/languages.

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": {
      "cohorts": "<cohorts>"
    },
    "name": "compare_collections"
  }
}

Input Schema

NameRequiredDescriptionDefault
cohortsYes
filtersNo

Output Schema

NameRequiredDescriptionDefault
cohortsYes
snapshot_idYes
overlap_noteYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • removedInput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
    • removedOutput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
    • removedOutput schema / additionalProperties
      Removed value: -false
    • removedOutput schema / properties / cohorts / items / additionalProperties
      Removed value: -false
    • changedOutput schema / properties / cohorts / items / properties / date_range / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "earliest": {
      -        "type": "number"
      -      },
      -      "latest": {
      -        "type": "number"
      -      }
      -    },
      -    "required": [
      -      "earliest",
      -      "latest"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "properties": {
      +      "earliest": {
      +        "type": "number"
      +      },
      +      "latest": {
      +        "type": "number"
      +      }
      +    },
      +    "required": [
      +      "earliest",
      +      "latest"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedOutput schema / properties / cohorts / items / properties / languages / propertyNames
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / cohorts / items / properties / missing / propertyNames
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / cohorts / items / properties / resource_types / propertyNames
      Removed value: -{
      -  "type": "string"
      -}
  2. Changed1 schema field changed
    • addedInput schema / properties / filters / properties / mentions_country
      Added value: +{
      +  "maxLength": 1000,
      +  "type": "string"
      +}
  3. Changed2 schema fields changed
    • removedInput schema / properties / filters / properties / location_id / maximum
      Removed value: -9007199254740991
    • changedInput schema / properties / filters / properties / project_id / anyOf
      Previous value: -[
      -  {
      -    "maxLength": 256,
      -    "type": "string"
      -  },
      -  {
      -    "exclusiveMinimum": 0,
      -    "maximum": 9007199254740991,
      -    "type": "integer"
      -  }
      -]New value: +[
      +  {
      +    "maxLength": 256,
      +    "type": "string"
      +  },
      +  {
      +    "exclusiveMinimum": 0,
      +    "type": "integer"
      +  }
      +]
  4. Added

TDQS

A3.8/5.0
Behavior3/5

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

The annotations already state readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds that output includes denominators, missingness, dates and top types/languages, but this overlaps an existing output schema, and it says nothing about cost, latency or behavior with invalid ids.

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?

Two tight sentences, front-loaded with the core action and cardinality, followed by the output summary. No filler or redundant restatement of the title.

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?

Coverage of cardinality, id source, shared-filter semantics and output shape makes this callable without guesswork, and the output schema carries return details. Minor gaps remain around invalid-id handling and what 'code' means.

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?

The description clarifies the cohorts parameter (2-4 items, each a project or collection referenced by id or code) and adds the important semantic that the same research-item filters apply across all cohorts, which the schema does not say. However, it leaves roughly twenty filter fields at 0% schema coverage completely undiscussed, so it only partly compensates.

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 (Compare), the exact resources (projects or collections), the cardinality (2-4), and the shared-filter constraint. An agent can distinguish it from list_collections or get_project without opening the schema.

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?

The definition says ids come from list_collections, which is a useful routing hint, and it implies use when you need a side-by-side cross-cohort comparison. However, it never states when NOT to use it, for example for a single-collection summary where get_collection_overview might do, so usage is only 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.