Skip to main content
Glama

KARP Research by SoulDriver

Apply for a free research grant

karp_grant_apply

Free, for agents without a wallet. Apply with what your agent researches and 1-3 real questions; get grant_key for 25 asks and 2 fact-checks (30 days) plus KARP's coverage of your questions. Pass grant_key to karp_ask and karp_check. One grant per client every 7 days. Copies of examples or of the template are refused. Ask your user before including a builder contact.

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": {
      "agent": "<agent>",
      "purpose": "<purpose>",
      "questions": "<questions>"
    },
    "name": "karp_grant_apply"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentYesName of the agent or app
builderNoOptional: URL or email of whoever runs it
purposeYesWhat the agent researches, and for whom
questionsYes1-3 real questions the agent needs answered

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false), the description discloses the grant's quota and expiry, the 7-day per-client rate limit, rejection conditions ('Copies of examples or of the template are refused'), and a privacy instruction to ask the user before including a builder contact. These are exactly the behavioral facts an agent needs before invoking a non-idempotent creation call.

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 eligibility hook is front-loaded, followed by the payoff, then usage wiring, then constraints. Every sentence carries distinct information with no filler or repetition of the schema.

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

Completeness5/5

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

For a non-idempotent creation tool with no output schema, the description covers the return value (grant_key), its quota and lifetime, the rate limit, refusal rules, and privacy handling. Nothing an agent needs in order to call it correctly appears to be missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: it explains that 'purpose' should describe what the agent researches, that 'questions' must be 1-3 real questions, and it constrains content (no copies of examples/templates) while flagging the builder field as requiring user consent.

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?

The description states a specific verb and resource ('Apply for a free research grant') and immediately names the concrete deliverable: a grant_key good for 25 asks and 2 fact-checks over 30 days. It also distinguishes this tool from siblings by saying the returned grant_key is what you pass to karp_ask and karp_check.

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?

It clearly frames eligibility ('Free, for agents without a wallet') and downstream usage (pass grant_key to karp_ask and karp_check), plus the re-application limit of one grant per client every 7 days. It does not explicitly contrast itself with karp_grant_terms or karp_coverage, so the when-not-to-use guidance is incomplete.

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