Skip to main content
Glama

browser_observe

browser_observe
Read-onlyIdempotent

Capture a page's state, interactive elements, accessibility data, and screenshot in one call to inspect a Chrome tab before acting. Scope it to a tab and pick which outputs to include.

Instructions

Capture page state, interactive elements, accessibility data, and a screenshot in one call.

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": {
      "tab_id": "<tab_id>"
    },
    "name": "browser_observe"
  }
}

Input Schema

NameRequiredDescriptionDefault
clipNo
tab_idYesChrome tab ID.
includeNo
full_pageNo
session_idNoSession that owns the tab. Pass it on every call so the runtime can refuse a tab another session holds.
image_formatNo
session_nameNoName for this conversation's Chrome tab group, so the tab bar reads as the task instead of a generated id. Sticky: pass it once when the name becomes clear, and again only to rename.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered structurally. The description adds that four distinct data classes come back together, but says nothing about the heaviness of the response, whether the screenshot is inline or referenced, or what happens when a subset is requested via include.

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 tight sentence with the verb first and the payloads enumerated; nothing is redundant. It is arguably too lean for a 7-parameter tool, but no wording is wasted.

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?

For a composite tool with a nested clip object and no output schema, the description should at least sketch the shape of the combined result or note that the four sections are returned together. It conveys the inputs' purpose but leaves the return structure and the interaction between include and the fixed list 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 43%, so several parameters (clip, full_page, image_format, include) carry no inline documentation. The description's four listed data classes map onto the include enum values, which is genuinely useful, but it adds nothing about clip coordinates, full_page behavior, or image format choice.

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?

The description gives a specific verb ('Capture') and enumerates the concrete payloads: page state, interactive elements, accessibility data, and a screenshot. It clearly reads as a bundled observation call, but it never names the granular siblings (browser_get_page, browser_get_interactives, browser_screenshot) it consolidates, so the differentiation is only implicit.

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?

'in one call' hints that this is the batch alternative to the individual getters, which implies when to reach for it. There is no explicit guidance on when to prefer this over the granular tools, nor any note about cost/size trade-offs of bundling a screenshot with everything else.

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