Skip to main content
Glama

browser_observe

Capture semantic state, frame mapping, and a locally masked screenshot with a DOM consistency flag to inspect browser tabs; animated pages may be inconsistent.

Instructions

Capture semantic state, frame mapping and a locally masked screenshot with a DOM consistency flag. Not an atomic render guarantee; animated or changing pages may be inconsistent.

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

Input Schema

NameRequiredDescriptionDefault
tabIdYesTab id from browser_tabs.
browserNoBrowser id from browser_list, or chrome/firefox when only one instance matches.
maxCharsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose two valuable traits: the screenshot is 'locally masked' (privacy behavior) and the capture is not an atomic render guarantee, so animated pages may be inconsistent. It omits other key traits an agent needs, such as whether the call is read-only/side-effect free, latency or size cost, and what to do when the consistency flag indicates a mismatch.

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?

Two tight sentences with the capability statement front-loaded and the caveat second; no filler. Slightly dense packing of four distinct outputs into one clause costs a point on immediate parseability.

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?

There is no output schema, so the description must convey return content, and it does list the four payload components. However, it leaves out truncation behavior via maxChars, whether the operation mutates anything, and how the DOM consistency flag should change the agent's next action, which is the main decision-relevant element of the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 67% and the description contributes nothing about any of the three parameters. In particular, maxChars governs truncation of returned semantic state but is never explained, and tabId/browser sourcing is left entirely to the schema.

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 concrete verb ('Capture') and enumerates the concrete outputs: semantic state, frame mapping, a locally masked screenshot, and a DOM consistency flag. This is clearly distinguishable from a plain screenshot or accessibility dump, though it never names the sibling tools it overlaps with (browser_screenshot, browser_snapshot, browser_accessibility).

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?

Usage is only implied by the caveat 'Not an atomic render guarantee; animated or changing pages may be inconsistent', which functions as a soft when-not-to-use hint. There is no explicit statement of when to prefer this over browser_screenshot or browser_snapshot, and no prerequisites or alternatives are named.

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