Skip to main content
Glama

KARP Research by SoulDriver

Check what KARP has researched (free)

karp_coverage
Read-onlyIdempotent

Free. Send the question you are researching, in plain words: KARP, SoulDriver's multi-model research engine, says whether its library covers it (covered / partial / none), with the match strength, the newest matching research date, matching titles and the tool to call next. Call it first, with your real question.

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": {
      "query": "<query>"
    },
    "name": "karp_coverage"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesThe question you are researching, in plain words. A specific question finds closer matches than a single keyword.
intentNoOptional: what you or your user are trying to find out, and what it is for (max 300 characters). Kept private; it helps decide what KARP researches next.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, closed-world behavior, so the safety profile is covered. The description adds genuinely new context: it is free, the caller should send the actual research question rather than keywords, and the response includes a recommended next tool — details no annotation conveys.

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?

Two sentences, front-loaded with cost ("Free.") and followed by the decisive instruction to call it first. The enumeration of return fields is dense but earns its place since there is no output schema; minor redundancy from restating 'question you are researching' twice.

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 no output schema, the description takes on the job of describing return values and does so for every field except match strength's format and any notion of limits. For a two-parameter read-only check tool this is nearly complete.

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%, so both query and intent are fully documented in the schema, including the 'specific question beats a keyword' hint. The description's "in plain words" and "use your real question" reinforce that guidance but add no new semantics, so baseline 3 applies.

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?

Names a specific action (checks whether KARP's research library covers a question) plus the exact return vocabulary (covered / partial / none, match strength, newest matching date, matching titles, next tool). An agent can tell this apart from karp_ask or karp_check from the description alone.

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?

"Call it first, with your real question" gives explicit ordering guidance relative to the research workflow. It stops short of naming which sibling to use instead when coverage is none/partial, leaving that to the returned next-tool field rather than stating it.

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.

Resources