Skip to main content
Glama

json_transform

Transform input JSON with an ordered pipeline of deterministic operations such as pick, flatten, filter, sort, dedupe, limit, count, and CSV export—no code execution or regex.

Instructions

Apply a pipeline of deterministic JSON operations (pick, get, flatten, filter_eq, sort_by, dedupe, limit, count, keys, to_csv) to the given data. No code execution or regex. Price about $0.005. Paid per call with x402 from your XRPL_SEED wallet (XRP or RLUSD, capped by MAX_*PER_CALL and SESSION_BUDGET*). Without a wallet it returns the price quote and charges nothing. Failed calls are not charged.

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": {
      "data": "<data>",
      "ops": "<ops>"
    },
    "name": "json_transform"
  }
}

Input Schema

NameRequiredDescriptionDefault
opsYesOperations in order, e.g. [{"op":"pick","fields":["a"]}]
dataYesInput JSON (object or array)
assetNoAsset to pay with on the XRP Ledger: XRP (default) or RLUSD

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full load, and it does so well for the payment dimension: price (~$0.005), the x402/XRPL_SEED mechanism, accepted assets, the MAX_*_PER_CALL and SESSION_BUDGET_* caps, the no-wallet quote path, and the fact that failed calls are not charged. The remaining gap is on the compute side — it never states the shape of the result (raw JSON vs. CSV string vs. integer for count) or what an unknown op does.

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?

The capability statement is front-loaded in the first sentence and the payment terms follow as a compact block; every sentence carries information, including the non-obvious 'failed calls are not charged'. The payment paragraph is dense with environment-variable names that could be tightened, costing it the top score.

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

Completeness3/5

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

For a 3-parameter tool with full schema coverage the inputs are well covered, but there is no output schema and the description never describes the return value — an agent cannot tell whether to_csv yields a string, whether count yields a number, or how errors surface. Combined with the absence of annotations, that leaves a real completeness hole for an otherwise strong definition.

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 genuine meaning beyond the schema: the schema only shows a single example op ('pick'), whereas the description enumerates all valid operation names and asserts the pipeline is ordered and deterministic. It still leaves per-op argument shapes (e.g. fields for sort_by, threshold for filter_eq) to be inferred, though the schema's example partly covers that.

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 opens with a specific verb and resource ('Apply a pipeline of deterministic JSON operations... to the given data') and goes further by enumerating the exact operation vocabulary (pick, get, flatten, filter_eq, sort_by, dedupe, limit, count, keys, to_csv). The clause 'No code execution or regex' actively distinguishes it from code-running siblings like call_paid_service and convert_file, so an agent can route correctly 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 Guidelines4/5

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

It clearly frames the use case (deterministic JSON reshaping, not arbitrary computation) and spells out the two runtime modes: with a wallet it charges and runs, without a wallet it returns a price quote only. What it lacks is an explicit 'use X instead when...' routing statement against the sibling tools, and it does not say what happens on invalid op names or malformed pipelines.

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