Skip to main content
Glama

read_window

Read-only

Read a window's buttons, fields, and text as compact lines with reference IDs for acting on them. Use it to inspect a specific window before clicking or typing via act_window.

Instructions

A window's buttons, fields and text as compact lines, e.g. [e34 button "Save" disabled]. Act on them with act_window using the e-refs; a new read_window (of any window) replaces them.

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": {
      "window": "<window>"
    },
    "name": "read_window"
  }
}

Input Schema

NameRequiredDescriptionDefault
windowYesWindow id from read_windows

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered; the description adds the higher-value behavior that the returned e-refs go stale on any subsequent read_window call of any window. It does not mention error cases (invalid window id) or whether reading changes focus, but the staleness contract is the non-obvious trait an agent needs.

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?

Two sentences: the first front-loads what is returned with a minimal illustrative example, the second gives the action and lifecycle rule. Zero filler and no restatement of the title or schema.

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

Completeness4/5

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

There is no output schema, so the description must carry the return format, and it does via the compact-line example plus the e-ref concept. For a one-parameter read tool that is essentially complete; only failure behavior for an unknown window id is unaddressed.

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 `window` parameter is already described in-schema as 'Window id from read_windows'. The description adds nothing about the parameter (no range, sourcing or multi-window behavior), so the baseline 3 applies.

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?

States a specific verb and resource (read a window's buttons, fields and text) and pins down the return shape with a concrete example line `[e34 button "Save" disabled]`. That example implicitly separates it from read_screenshot (an image) and read_windows (an id list).

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?

Explicitly routes follow-up action to the sibling `act_window` using the emitted e-refs, and states the invalidation rule (a new read_window of any window replaces them). It stops short of saying when to prefer this over read_screenshot for the same window, so it is clear context rather than full when/when-not guidance.

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