Skip to main content
Glama

Northwestern University Libraries Digital Collections API

by io.github.nulib

Search for Similar Works

similarity-search
Read-onlyIdempotent

Find works that are similar to a given work. Uses semantic similarity based on work embeddings.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoThe page of search results to return
work_idYesID of a work to find similar items for.
max_resultsNoThe maximum number of search results to return per page
public_onlyNoOnly include publicly available works in search results

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataYesThe search results returned from the Digital Collections API
infoYes
explainNoThe explain output from Elasticsearch for the search query. Only included if the MCP is running in debug mode.
paginationYes
aggregationsNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare this as read-only, idempotent, and non-destructive, so the description does not need to repeat those traits. It adds useful context by explaining the results come from semantic embeddings, but it does not disclose further behavioral details such as result ranking or pagination behavior. This is acceptable given the strong annotation coverage.

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?

The description is two short, front-loaded sentences with no redundant language. It conveys the core purpose and the mechanism without wasting the agent's attention.

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, full parameter documentation, and safety-related annotations, the description is largely complete for invoking the tool correctly. The only meaningful gap is the lack of guidance around sibling tools, but that is more about routing than about calling this tool successfully.

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 description coverage is 100%, and the schema already documents work_id, page, max_results, and public_only with defaults and bounds. The description adds no parameter-specific meaning, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific action and resource: 'Find works that are similar to a given work.' The added mechanism 'semantic similarity based on work embeddings' clarifies how results are computed. It is unambiguous, though it does not explicitly distinguish itself from sibling tools like view-similar-works, so it stops short of full differentiation.

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 use case is clear from the first sentence, but the description gives no explicit guidance on when to use this tool instead of related siblings such as search or view-similar-works. No exclusions or alternatives are mentioned, leaving the routing decision to the agent.

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

All Northwestern University Libraries Digital Collections API toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.4/5.0
Disambiguation4/5

Most tools have clear boundaries: search and similarity-search are distinct query modes, and view-* tools are explicitly for interactive viewing while get-work and list-collections return metadata. However, get-work vs view-work and list-collections vs view-collection could cause mild confusion, and view-search-results refers to a 'search-works' tool that is actually named 'search'.

Naming Consistency3/5

Tool names mostly follow a lowercase hyphenated verb-object pattern like get-work, list-collections, and view-work. However, 'search' lacks an object, 'similarity-search' is formatted as a compound noun rather than a verb phrase, and the description for view-search-results references a non-existent 'search-works' tool name.

Tool Count5/5

Eight tools is a well-scoped set for a digital collections API. Each tool serves a distinct function covering search, retrieval, similarity, and interactive viewing without feeling bloated or sparse.

Completeness4/5

The tool surface covers the core read-only workflows: searching, similarity matching, retrieving work metadata, listing collections, and viewing results interactively. A minor gap is the lack of a direct get-collection metadata tool separate from list-collections, but agents can likely work around this.

Resources