Skip to main content
Glama

Observe page

browser_observe

Reads a page deterministically without a model call, returning URL, title, visible text, and interactive element refs so you can decide and act via click, type, select, or press.

Instructions

Deterministic page read — free, no model call. Returns URL, title, visible text (article/main content preferred over nav chrome), and interactive elements as refs (e1, e2, ...), offscreen ones marked. Use this when you want to decide and act yourself via browser_click / browser_type / browser_select / browser_press. Use browser_run or browser_act to delegate the deciding to Jev instead. The output is windowed to max_elements; the underlying action pool is larger — use browser_find for elements beyond the window.

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": "browser_observe"
  }
}

Input Schema

NameRequiredDescriptionDefault
max_charsNoCap on returned visible text (default 6000).
max_elementsNoHow many elements to return (default 250; the action pool holds up to 1200).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and discloses useful traits: free/no model call, deterministic read, article/main content preference, offscreen-element marking, and windowed output tied to a larger action pool. It does not explicitly state read-only/no-side-effects behavior or error conditions such as no page being open, but the core behavior is well disclosed.

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?

The description is four compact sentences, front-loaded with what the tool returns and followed by usage routing and the element-window limitation. Every sentence adds distinct information, and there is no redundant restatement of the 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 appropriately explains the returned URL, title, visible text, and element refs. It covers both parameters and the main alternatives, though it could mention edge cases such as what happens when no page is open.

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 100%, and the schema already documents max_chars and max_elements with defaults and caps. The description adds meaningful context beyond the schema by explaining that output is windowed to max_elements while the action pool is larger, and by routing to browser_find for elements outside that window.

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?

The description states a specific verb and resource: a deterministic page read returning URL, title, visible text, and interactive element refs. It explicitly distinguishes this tool from browser_run/browser_act and browser_find, so an agent can identify its role without opening sibling schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use guidance: use this when you want to decide and act yourself via browser_click, browser_type, browser_select, or browser_press. It also names the alternatives and their selecting conditions: browser_run/browser_act when delegating decisions, and browser_find for elements beyond the returned window.

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