Skip to main content
Glama
Sign In
CDPM

CDPM

by IGELHARINE
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Snapshot

browser_snapshot

Captures a browser tab as accessibility-tree text, giving refs for clickable/typable elements and filters for paging, search, and subtrees.

Instructions

Reads the tab as accessibility-tree text. Clickable/typable elements get refs like [e12]. Long pages are split; only page 1 (top) is shown (page=2 to continue; refs stay the same across pages). find="text" shows only matching elements with their parent context; ref="e40" shows only that element's subtree. Refs change when the page changes, so re-snapshot before acting.

Input Schema

NameRequiredDescriptionDefault
refNoOnly this ref element and its subtree
tabNoTarget tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs.
findNoOnly lines containing this text, with parent context (ignores case and spaces). If unsure of site language, use | for alternatives, e.g. "제목|subject"
pageNoPage number for long output (default 1)
slotYesBrowser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049.
agentNoYour display name, shown to other agents. Subagents must always set it. Default "claude-1e1b".
multiSlotNotrue only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
interactiveNoOnly actionable elements (lines with refs): inputs, buttons, links. Use first to find inputs on big pages like Gmail

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.10
    • changedInput schema / properties / agent / description
      Previous value: -"Your display name, shown to other agents. Subagents must always set it. Default \"claude-68d9\"."New value: +"Your display name, shown to other agents. Subagents must always set it. Default \"claude-1e1b\"."
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and delivers: refs are assigned as [e12], long pages are paginated with refs stable across pages, find and ref narrowing behavior are described, and critically it warns 'Refs change when the page changes, so re-snapshot before acting' — a non-obvious, action-relevant behavioral trait.

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?

Front-loaded with the core purpose, then dense behavioral facts, ending on the most important operational warning. Every sentence conveys distinct, actionable information with no filler.

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?

For an 8-param, no-output-schema tool, the description explains the return shape (a11y tree with refs), pagination, and ref lifecycle well. Slot/tab/agent/multiSlot semantics are left entirely to the schema, which is acceptable given their 100% coverage, but the description adds nothing about them.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema: it documents cross-page ref stability (schema says only 'page=2 to continue') and gives concrete usage examples for find ("text") and ref ("e40") subtree behavior.

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: 'Reads the tab as accessibility-tree text.' This immediately separates it from siblings like browser_text (raw text) and browser_screenshot (image) by naming the distinct output format and the ref-annotated tree structure.

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 clear workflow context: 're-snapshot before acting' establishes that this must precede action tools, and the find/ref guidance explains situational usage. It stops short of explicitly naming when to prefer this over browser_text or browser_screenshot, so no exclusions are stated.

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

Deploy Server

Other Tools