Skip to main content
Glama

Axad

Correction

show_correction
Read-only

Displays a check of the learner's own writing in a language they learn: what they wrote, the corrected text with the changes marked, a short reason for each fix, and a more natural version.

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": {
      "wrote": "<wrote>",
      "fixed": "<fixed>",
      "ok": "<ok>",
      "fixes": "<fixes>",
      "lang": "<lang>"
    },
    "name": "show_correction"
  }
}

Input Schema

NameRequiredDescriptionDefault
okYes
foldNotrue: a secondary widget of this reply, made now and shown folded: only its title row, until one click opens it. Omit it on the reply's main widgets, which show open.
langYesBCP 47 code of the language the widget teaches: "nl". The view speaks and saves its words in it.
nextNoUp to 3 one-tap next steps shown under the widget: label is the button's text, ask the message a tap sends.
fixedYes
fixesYes
glossNo
wroteYes
naturalNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / next
      Added value: +{
      +  "description": "Up to 3 one-tap next steps shown under the widget: label is the button's text, ask the message a tap sends.",
      +  "items": {
      +    "properties": {
      +      "ask": {
      +        "description": "The message a tap sends, in the learner's words.",
      +        "maxLength": 300,
      +        "type": "string"
      +      },
      +      "label": {
      +        "description": "The button's text.",
      +        "maxLength": 32,
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "label",
      +      "ask"
      +    ],
      +    "type": "object"
      +  },
      +  "maxItems": 3,
      +  "type": "array"
      +}
  2. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the useful disclosure of what the rendered view contains (original, marked corrections, per-fix reasons, natural rewrite), but says nothing about persistence, whether the correction is stored, or what happens on repeated calls.

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?

A single front-loaded sentence with no filler, and the payload is listed in the order it appears in the view. The trailing comma list is dense but every clause carries information.

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?

No output schema exists, and the description does cover the return content, while annotations carry the safety profile. However, for a 9-parameter widget at 33% schema coverage, the unexplained ok and gloss fields plus the undocumented fold/next behavior leave gaps an agent must guess at.

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 only 33%, so the description must compensate, and it does for the core payload: wrote, fixed, fixes and natural are each explained by the enumerated content list. The remaining ambiguity is ok and gloss, which are undocumented in both schema and description.

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?

A specific verb ("Displays") plus a precise resource ("a check of the learner's own writing in a language they learn"), followed by exactly what the view contains. An agent can distinguish this from siblings like show_explain or show_alternatives, though it never names them explicitly.

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 tool is for showing corrections of the learner's own written text. There is no statement of when to prefer it over show_alternatives, show_explain, or show_visual, and no prerequisites such as needing the original text before calling.

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.