Skip to main content
Glama
Mehmoodqureshi

MCP Browser Extension

by Mehmoodqureshi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

snapshot

Capture interactive accessibility elements with stable refs to target reliably instead of guessing CSS selectors; use diff mode to return only changes since the last capture.

Instructions

Accessibility snapshot: interactive elements with refs to target by ref (more reliable than guessing CSS selectors). Pass diff:true to get only what changed since the last snapshot of this tab - far cheaper in a click/read loop. Password fields appear as secret:true with no value.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
maxNo
diffNoReturn added/removed/changed elements since the previous snapshot of this tab instead of the whole tree
tabIdNoTab id (default: agent's tab)
frameIdNoFrame id from frames_list
allFramesNoAct on the first match in ANY frame (the element may be in an iframe)
failOnAuthWallNoError with [AUTH_REQUIRED] if this lands on a sign-in wall (expired session)
interactiveOnlyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.9.24
    • changedInput schema / properties / tabId / description
      Previous value: -"Tab id (default: active tab)"New value: +"Tab id (default: agent's tab)"
  2. Changed4 schema fields changedv0.9.5
    • changedInput schema / properties / allFrames / description
      Previous value: -"Search every frame of the tab and act on the first that matches - use when a selector should match but does not (the element is in an iframe)"New value: +"Act on the first match in ANY frame (the element may be in an iframe)"
    • changedInput schema / properties / failOnAuthWall / description
      Previous value: -"Fail with [AUTH_REQUIRED] when the page this call lands on is a high-confidence sign-in wall (session expired). Off by default unless the server runs with --fail-on-auth-wall; snapshot still reports the verdict as `authWall` either way."New value: +"Error with [AUTH_REQUIRED] if this lands on a sign-in wall (expired session)"
    • changedInput schema / properties / frameId / description
      Previous value: -"Act inside this frame (ids come from frames_list)"New value: +"Frame id from frames_list"
    • changedInput schema / properties / tabId / description
      Previous value: -"Target tab id (defaults to the active tab)"New value: +"Tab id (default: active tab)"
  3. Changed1 schema field changedv0.9.3
    • addedInput schema / properties / failOnAuthWall
      Added value: +{
+  "description": "Fail with [AUTH_REQUIRED] when the page this call lands on is a high-confidence sign-in wall (session expired). Off by default unless the server runs with --fail-on-auth-wall; snapshot still reports the verdict as `authWall` either way.",
+  "type": "boolean"
+}
  4. Changed3 schema fields changedv0.7.0
    • addedInput schema / properties / allFrames
      Added value: +{
+  "description": "Search every frame of the tab and act on the first that matches - use when a selector should match but does not (the element is in an iframe)",
+  "type": "boolean"
+}
    • addedInput schema / properties / diff
      Added value: +{
+  "description": "Return added/removed/changed elements since the previous snapshot of this tab instead of the whole tree",
+  "type": "boolean"
+}
    • addedInput schema / properties / frameId
      Added value: +{
+  "description": "Act inside this frame (ids come from frames_list)",
+  "type": "number"
+}
  5. First observedv0.6.2

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations the description carries the full burden. It usefully discloses that the last snapshot defines the diff baseline, and that password fields are masked as secret:true with no value. It omits broader behavior: return shape, auth-wall handling (only hinted via the schema's failOnAuthWall), frame scoping, and error behavior.

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?

Three tight sentences with the primary purpose front-loaded and each clause carrying weight (ref targeting, diff cost, secret fields). Parentheticals are dense but not wasteful; it could be marginally cleaner but there is no filler.

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?

For a 7-parameter, annotation-free tool with no output schema, the description covers diff, refs, and password masking but says nothing about max, tabId/frameId/allFrames scoping, interactiveOnly, or the returned tree structure. Adequate but with clear gaps an agent must infer from the schema.

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 description coverage is 71%, so the schema documents most parameters itself (diff, tabId, frameId, allFrames, failOnAuthWall). The description adds only the diff baseline semantics and the secret-field note, not new meaning for max or interactiveOnly. Baseline 3 is appropriate.

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 specific artifact (accessibility snapshot of interactive elements) and the key output (refs for targeting). It implicitly distinguishes itself from get_html/get_text/screenshot by emphasizing ref-based targeting and reliability over CSS selectors, but it never names a sibling directly.

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?

It explains the click/read loop use case and recommends diff:true as cheaper, which implies usage. However it never states when to prefer this over get_html, read_as_markdown, or screenshot, and gives no explicit exclusions or preconditions.

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