TerminalMCP

json_tool

Query and patch JSON at dotted paths without rewriting whole files. Get, set, delete, merge, list keys, validate, and format on a file or inline text.

Instructions

Query and patch JSON without rewriting the whole file: get (read a path), set, delete, merge (deep), keys (list a level), validate, format (pretty-print or minify). Paths look like "scripts.build" or "items[0].name". Works on a file (path=) or inline text (content=).

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": {
      "action": "<action>"
    },
    "name": "json_tool"
  }
}

Input Schema

Name	Required	Description
`path`	No	JSON file to read (and write, for set/delete/merge/format).
`value`	No	set: the new value (any JSON type). merge: the object to merge in.
`action`	Yes	What to do.
`indent`	No	Indent for written/formatted output. Default 2; 0 minifies.
`content`	No	Inline JSON text instead of a file. Nothing is written in this mode.
`json_path`	No	Dotted/bracketed path inside the document, e.g. "a.b[0].c". Omit for the root.
`max_bytes`	No	Byte cap on returned output.
`create_missing`	No	set: create intermediate objects that do not exist. Default true.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 12, 2026

TDQS

A4.3/5.0

Behavior4/5

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

No annotations are supplied, so the description carries the burden, and it does useful work: 'without rewriting the whole file' discloses the partial-mutation behavior, and 'Nothing is written in this mode' clearly marks the content= mode as non-destructive. It omits auth/permission needs, error behavior on missing paths, and write scope beyond path=.

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?

One dense paragraph with the core value proposition ('without rewriting the whole file') front-loaded, followed by the action list, path syntax, and mode selection. Every clause earns its place, though the action enumeration and examples make it slightly list-heavy.

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?

For an 8-parameter, 7-action tool with no annotations and no output schema, the description covers actions, path syntax, and file-vs-inline modes well. It does not describe return values or per-action error semantics, which is a modest gap given there is no output schema.

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 baseline is 3; the description adds value by giving concrete path syntax ('scripts.build', 'items[0].name') and clarifying that content= is inline and produces no writes. It still leaves the value/create_missing/max_bytes semantics to the schema.

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 names a specific verb+resource and enumerates every action (get, set, delete, merge, keys, validate, format) so the agent knows exactly what the tool covers. It also distinguishes itself from generic file siblings with 'without rewriting the whole file', signaling a JSON-aware partial-patch tool rather than file_read/file_write/file_edit.

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 states the two operating modes ('Works on a file (path=) or inline text (content=)'), which tells the agent when to supply which parameter. It does not explicitly say when to prefer this over file_edit or file_read, so it stops short of full routing guidance.

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

Deploy Server