Skip to main content
Glama
cdp-bridge
by Unagi-cq

browser_observe

Lists visible interactive controls on a browser tab as short-lived references for actions, with a page revision to detect stale refs. Re-observe after navigation or actions.

Instructions

List visible interactive controls on a tab with short-lived references.

Args: tab_id: Tab to observe. Uses the active MCP tab if empty. limit: Maximum controls to return, up to 150.

Returns a page_revision and control refs for browser_act. Observe again after an action, navigation, or a stale-reference response.

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
limitNo
tab_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.25

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and does well: it discloses that refs are short-lived, that there is a hard cap of 150 controls, that a page_revision is returned, and that refs go stale after actions or navigation. It does not state the read-only/idempotent nature or any permission requirements, which is the remaining gap for a tool with zero annotation coverage.

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 short paragraphs plus an Args block, with the purpose front-loaded and the refresh rule at the end where a caller will look for it. The Args lines largely restate parameter names already in the schema, which is mild redundancy but keeps the prose self-contained.

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?

An output schema exists, so return-value detail is not required, and the description still flags page_revision and control refs so the agent knows to stash them. With zero required parameters and a simple two-field schema, the only missing pieces are the read-only guarantee and tab_id's format, neither of which blocks a correct call.

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 description coverage is 0%, so the description must compensate, and its Args block does: tab_id is documented as falling back to the active MCP tab (the schema's empty-string default is uninformative), and limit is documented with a hard maximum of 150 that the schema never states. It does not reconcile the schema's default of 80 against that cap, leaving a small ambiguity.

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 — 'List visible interactive controls on a tab' — with the qualifying detail that the returned references are short-lived. It also names browser_act as the consumer of those refs, so an agent can immediately tell this is the read/discovery half of a read-then-act pair.

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?

Gives an explicit refresh policy: 'Observe again after an action, navigation, or a stale-reference response,' which tells the agent exactly when to re-call. It lacks an explicit when-not-to-use statement or a named alternative for non-interactive page reading, so it stops short of a 5.

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