Skip to main content
Glama
aic0t

AI Coach MCP Server

by aic0t

Preview a local file in AI Coach

show_ai_coach_file
Idempotent

Open a local file in a private, sandboxed preview beside the AI Coach mascot. Works with Markdown, text, diagrams, images, and HTML without exposing file contents to the model.

Instructions

Open a safe local preview beside the AI Coach mascot (md, markdown, txt, mmd, mermaid, html, htm, jpg, jpeg, png, heic, webp, svg; HTML is sandboxed). The file is read only by the AI Coach app; its contents are never returned to the model. Use only for a file the user asked to preview or one created in the current task.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYesAbsolute path of the local file to preview. Allowed: md, markdown, txt, mmd, mermaid, html, htm, jpg, jpeg, png, heic, webp, svg.
localeNoDisplay language (BCP 47).
mascotIdNoA mascotId returned by status. Defaults to the primary mascot when omitted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.4
    • changedInput schema / properties / locale / description
      Previous value: -"Display language hint (BCP 47). The dashboard view passes hostContext.locale through unchanged."New value: +"Display language (BCP 47)."
    • changedOutput schema / (root)
      Previous value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "connection": {
      -      "enum": [
      -        "connected",
      -        "app_unavailable",
      -        "incompatible"
      -      ],
      -      "type": "string"
      -    },
      -    "error": {
      -      "additionalProperties": false,
      -      "properties": {
      -        "code": {
      -          "type": "string"
      -        },
      -        "reason": {
      -          "type": "string"
      -        },
      -        "retryable": {
      -          "type": "boolean"
      -        }
      -      },
      -      "required": [
      -        "code",
      -        "retryable"
      -      ],
      -      "type": "object"
      -    },
      -    "fileName": {
      -      "type": "string"
      -    },
      -    "fileType": {
      -      "enum": [
      -        "markdown",
      -        "text",
      -        "mermaid",
      -        "html",
      -        "image"
      -      ],
      -      "type": "string"
      -    },
      -    "mascotId": {
      -      "type": "string"
      -    },
      -    "protocolVersion": {
      -      "const": 1,
      -      "type": "number"
      -    },
      -    "shown": {
      -      "type": "boolean"
      -    },
      -    "sizeBytes": {
      -      "minimum": 0,
      -      "type": "integer"
      -    },
      -    "updatedAt": {
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "protocolVersion",
      -    "connection",
      -    "shown",
      -    "updatedAt"
      -  ],
      -  "type": "object"
      -}New value: +null
  2. First observedv0.1.2

TDQS

A4.5/5.0
Behavior5/5

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

The description adds meaningful behavior beyond the annotations: HTML is sandboxed, the file is read only by the app, and contents are never returned to the model. This privacy/security context is genuinely valuable for the agent when deciding whether to use the tool. The readOnlyHint=false annotation is not contradicted because the tool still opens a UI preview.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: the core purpose appears in the first clause, supported formats follow immediately, and the usage restriction is stated in one clear sentence. There is no filler or redundant material.

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

Completeness5/5

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

The description provides everything an agent needs to invoke the tool correctly: allowed formats, sandboxing, privacy behavior, and the exact condition under which use is permitted. Even without an output schema, saying contents are never returned to the model prevents the agent from expecting file content as a return value.

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 the schema already documents path, locale, and mascotId. The description repeats the allowed extensions and mentions HTML sandboxing, but does not add meaningful semantics for locale or mascotId beyond what the schema provides. This meets the baseline without exceeding it.

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 precise action ('Open a safe local preview'), the resource ('local file'), and the context ('beside the AI Coach mascot'), and explicitly enumerates supported file types. This clearly differentiates it from sibling show tools like show_ai_coach_message or show_ai_coach_git_graph, which target different content.

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 gives an explicit usage gate: 'Use only for a file the user asked to preview or one created in the current task,' telling the agent when the tool is appropriate and implicitly when it is not. However, it does not explicitly name alternatives such as read_ai_coach_note for cases where the model actually needs the file contents.

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