Skip to main content
Glama

Tinplate Edge AI Safety, Security & EU Compliance

tinplate_json_heal

Read-onlyIdempotent

Broken JSON & LLM Output Healer API: Repair malformed or truncated LLM JSON outputs into valid, schema-checked JSON in 1 ms. (Endpoint: POST /v1/json-heal)

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": {
      "raw": "<raw>"
    },
    "name": "tinplate_json_heal"
  }
}

Input Schema

NameRequiredDescriptionDefault
rawYesMalformed JSON or LLM output string (max 256 KB).
schemaNoOptional JSON Schema (draft subset) to validate the healed JSON against without eval.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / schema / additionalProperties / nullable
      Removed value: -true
  2. Changed5 schema fields changed
    • changedInput schema / properties / raw / description
      Previous value: -"Parameter 'raw' (e.g. \"Sure! Here is the JSON:\\n```json\\n{\\\"name\\\": \\\"Ada\\\", 'active': Tr\")"New value: +"Malformed JSON or LLM output string (max 256 KB)."
    • addedInput schema / properties / raw / example
      Added value: +"```json\n{ name: 'Tinplate', tags: ['api', 'edge',], active: True, }\n```"
    • addedInput schema / properties / raw / maxLength
      Added value: +262144
    • addedInput schema / properties / raw / minLength
      Added value: +1
    • addedInput schema / properties / schema
      Added value: +{
      +  "additionalProperties": {
      +    "nullable": true
      +  },
      +  "description": "Optional JSON Schema (draft subset) to validate the healed JSON against without eval.",
      +  "example": {
      +    "properties": {
      +      "active": {
      +        "type": "boolean"
      +      },
      +      "name": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "name",
      +      "active"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "object"
      +}
  3. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds latency ('1 ms') and the fact that output is schema-checked, which is useful. It does not state what happens when healing fails or when the optional schema fails validation, which is the main behavioral unknown for a repair tool.

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 compact clauses with the core capability front-loaded and no filler. The trailing '(Endpoint: POST /v1/json-heal)' is arguably redundant metadata for an MCP caller and is the only marginally wasteful element.

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?

With only two well-documented parameters this is close to complete, but there is no output schema and the description never says what the tool returns (healed JSON alone, or healed plus validation errors). For a repair tool whose failure mode is unrepairable input, that return/error behavior should be stated.

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 description coverage is 100%, so both parameters are already documented in the schema with examples and a max length. The description's 'schema-checked' phrase reinforces the role of the optional schema parameter but adds no format or failure semantics beyond the schema text, making the baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource: 'Repair malformed or truncated LLM JSON outputs into valid, schema-checked JSON.' An agent can tell this is a JSON-repair tool rather than a validator. It stops short of differentiating itself from close siblings such as tinplate_llm_output_guard or tinplate_locale_value_parser, which a reader must infer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is only implied: the input conditions (malformed or truncated JSON) signal when the tool applies, but there is no explicit when-to-use or when-not guidance and no named alternative. The relationship to sibling guard/parser tools is left for the agent to guess.

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