Skip to main content
Glama

screen_look

Read-only

See the page or app you opened: every element a person could act on (ref, role, name, box; a field's value, never a password), the headings, scroll, and a screenshot. Refs are valid until the next look.

response_detail (summary|ids|compact|full), fields (dotted paths), cursor (next page) — see the server instructions.

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": "screen_look"
  }
}

Input Schema

NameRequiredDescriptionDefault
cursorNo
fieldsNo
screenshotNo
response_detailNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare read-only and non-destructive, so the lower bar applies. The description still adds genuinely useful behavior: refs go stale after the next look (explaining the non-idempotent hint), password values are never returned, results paginate via cursor, and a screenshot is included. It doesn't say what happens on an invalid cursor or what an empty page looks like.

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?

Front-loaded with the core purpose, then a compact parameter line. Dense but every clause carries information; the closing 'see the server instructions' is a mild deflection but short.

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?

No output schema exists, so the description does the work of describing the return payload, and it does so concretely. The main gap is the undocumented 'screenshot' input flag and no statement of page-size or pagination termination, which matters for a tool that can return large element lists.

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 0%, so the description must carry the load, and it does for three of four parameters: it supplies the enum values for response_detail (summary|ids|compact|full), explains fields as dotted paths, and identifies cursor as next-page. The boolean 'screenshot' parameter is never described — the phrase 'and a screenshot' refers to output content, leaving the input flag ambiguous.

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?

States a specific verb and resource ('See the page or app you opened') and enumerates what comes back: actionable elements with ref/role/name/box, field values, headings, scroll position, and a screenshot. This clearly separates it from write-oriented siblings like screen_act and from screen_result, though it never names an alternative 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?

'The page or app you opened' and 'Refs are valid until the next look' imply it is called after opening a page and re-called after any interaction, which is real usage guidance. However, there is no explicit statement of when to use this versus screen_result or media_look, nor any exclusion conditions.

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.