Fix broken or incomplete JSON, including text from language models.
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "json_repair"
}
}| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does little with it. It does not say whether repair is best-effort or strict, whether malformed input is rejected, whether the original content is preserved or altered, or what the caller receives back — all material for a fix-up tool whose output shape is undefined.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with zero filler; the most important clause (fix broken JSON) leads. It is arguably too terse for a tool with no annotations or output schema, but there is no wasted wording to cut.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no annotations, no output schema, and an untyped request body, so the description is the sole source of behavioral information — and it supplies only one line. Failure modes, return format, and input payload shape all remain unstated.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Parameter count is zero, giving a baseline of 4, but the schema is an open POST body (additionalProperties: true) with no named properties, and the description says nothing about how the JSON to repair is supplied. That leaves the only real input — the payload — undocumented in both places.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource: "Fix broken or incomplete JSON," plus the notable scope addition "including text from language models." An agent can tell this is a repair tool, but the description never names or contrasts the adjacent json_format sibling, so the repair-vs-reformat boundary is left to inference.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"Broken or incomplete" implies the triggering condition, and the LLM-text clause hints at a common source of malformed input. There is no explicit when-to-use vs json_format, no statement of what counts as repairable (truncation? trailing commas? prose-wrapped output?), and no guidance on when to give up.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.