Skip to main content
Glama

glass_capabilities

Read-only

Report backend support and setup details, or inspect the active session for input support, desktop interference, and the selected accessibility reader.

Instructions

Backend support and setup. Session scope reports input support, desktop_interference, and the selected accessibility reader when available.

Tool call template

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": "glass_capabilities"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopeNobackend (default) or active session.
backendNoBackend name, defaulting to active/default; session scope requires a match.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.9.0
    • changedInput schema / properties / backend / description
      Previous value: -"x11, wayland, windows, macos, android or ios. Default active/default backend. Valid but unbuilt backends report available:false."New value: +"Backend name, defaulting to active/default; session scope requires a match."
    • addedInput schema / properties / scope
      Added value: +{
      +  "description": "backend (default) or active session.",
      +  "enum": [
      +    "backend",
      +    "session",
      +    null
      +  ],
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  2. Changed1 schema field changedv1.8.0
    • changedInput schema / properties / backend / description
      Previous value: -"Which backend to report: `x11`, `wayland`, `windows`, `macos`, `android`, or\n`ios`. Omit for the active/default backend (`GLASS_BACKEND`, else the host\ndefault). A valid name for a backend not built into this binary reports\n`available: false`."New value: +"x11, wayland, windows, macos, android or ios. Default active/default backend. Valid but unbuilt backends report available:false."
  3. Addedv1.2.0
  4. Removedv1.1.0
  5. Addedv1.0.3

TDQS

C2.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds one useful behavioral detail — that session scope returns input support, desktop_interference, and the selected accessibility reader — but says nothing about what backend scope reports or what happens if no session is active.

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

Conciseness3/5

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

Only two short sentences, so nothing is bloated, but the opening sentence is vague filler that doesn't front-load the actual function. The informative part (what session scope returns) arrives second and only partly compensates.

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

Completeness2/5

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

For a read-only discovery tool with no output schema, the description should explain what the caller gets back in each scope; it covers session scope partially but leaves backend scope and the return shape unspecified. An agent cannot predict the response structure from this definition.

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 coverage is 100% and the enum plus the "session scope requires a match" constraint are documented in the schema itself. The description only loosely echoes the scope distinction without adding format, default, or failure semantics beyond it.

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

Purpose2/5

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

"Backend support and setup" is a vague noun phrase with no clear verb or resource; it could describe discovery, configuration, or diagnostics. Only the second sentence hints at a reporting function, and the actual subject (capabilities of a backend) is never stated outright.

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

Usage Guidelines2/5

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

No guidance on when to call this versus alternatives such as glass_doctor or glass_start, and no precondition for choosing backend scope over session scope beyond what the schema already says. The agent must infer the use case entirely.

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