Skip to main content
Glama
@caelaralabs/mcp

@caelaralabs/mcp

caelara_docs_dedupe_fuzzy_matcher

Cluster near-duplicate strings with Jaro-Winkler and token similarity to group similar items and support deduplication at a configurable threshold.

Instructions

[Document Utilities] Cluster near-duplicate strings using Jaro-Winkler and token similarity Measured p50 10 ms, p95 14 ms (2026-11-21, benchmarks.caelaralabs.com). Calls https://docs.caelaralabs.com.

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": {
      "items": "<items>"
    },
    "name": "caelara_docs_dedupe_fuzzy_matcher"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsYesArray of strings
thresholdNoSimilarity threshold 0.5-1 (default 0.88)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.1/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full behavioral burden; it does add useful operational context in the form of expected latency (p50 10 ms, p95 14 ms) and a documentation URL. However, it never states the shape of the result (clusters versus pairwise matches) or how threshold changes affect grouping, which is the key unknown for a clustering operation.

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?

Short and front-loaded, leading with the bracketed category and the core action before benchmarks and the docs pointer. The benchmark citation and URL are boilerplate but brief; a missing sentence break after "token similarity" is a minor blemish.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This tool has no annotations and no output schema, so the description is the only source of behavioral expectations, yet it never explains what comes back (grouped clusters, match pairs, scores) or how the threshold influences results. For a fuzzy-clustering operation whose output structure is inherently non-obvious, that omission leaves an agent unable to plan around the response.

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%, with both `items` and `threshold` (0.5-1, default 0.88) documented inline. The description adds algorithm context but no meaning beyond the schema for either parameter, so the baseline of 3 applies.

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 verb and resource: "Cluster near-duplicate strings," and names the underlying methods (Jaro-Winkler plus token similarity), which tells an agent this is fuzzy grouping rather than exact matching. It does not explicitly differentiate from siblings such as the sanctions fuzzy screener or the address normalizer, so the agent must infer the boundary from domain naming alone.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no statement of conditions or exclusions, and no named alternative for cases where exact matching or a different threshold strategy is wanted. The agent is left to infer applicability purely from the word "near-duplicate."

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

Deploy Server

Other Tools