Skip to main content
Glama

observe

Reads a browser page as compact, token-budgeted text and returns element IDs for use with the act tool.

Instructions

Read the page of a browser started with start_browser, as compact text: one line per element, [id] role "name" state, inside a token budget. Use the ids with the act tool. No Playwright or CDP needed, and no extra charge. Ids stay valid across observe and act calls until the page loads a new document. On a full-page bot check nothing is read and the first lines say so.

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": {
      "browser_id": "<browser_id>"
    },
    "name": "observe"
  }
}

Input Schema

NameRequiredDescriptionDefault
tabNoTab id, from the tabs line of an earlier observe. Default: the tab used last.
scopeNoviewport (default): what is in the viewport, the rest counted. page: the whole page.
budgetNoApproximate tokens for the view. Default 2000.
expandNoId of a container, table, list or select to list in full.
browser_idYesThe id returned by start_browser.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.2

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses output shape, a token budget, cost ('no extra charge'), prerequisites ('no Playwright or CDP needed'), and the id-lifetime rule (valid across observe/act until a new document loads). The one unusual failure mode, a full-page bot check yielding nothing with an explanatory header, is also disclosed. It omits what happens on an invalid or expired browser_id.

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 purpose, then the id contract, then cost and edge cases; nearly every sentence adds a fact. Density comes at the cost of flow, and the bot-check sentence is terse to the point of being cryptic.

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

Completeness5/5

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

For a five-parameter read tool with no output schema and no annotations, the description supplies the output format, defaults context, cost, id lifetime and the notable empty-result case. An agent has enough to call it correctly and interpret what comes back.

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%, so tab, scope, budget, expand and browser_id are already documented in the schema. The description reinforces the budget and id-lifetime concepts but adds no syntax or default detail beyond the schema, which matches the baseline for fully documented parameters.

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 the page of a browser started with start_browser') plus the output form ('one line per element, [id] role "name" state'). It cleanly separates itself from start_browser (which launches) and act (which consumes the ids).

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?

Makes the position in the workflow explicit: the browser must have been started with start_browser, and the returned ids are meant to be passed to act. It stops short of stating when not to use it (e.g., prefer a task/run_task for fully automated flows), so it is clear but not complete routing guidance.

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