Skip to main content
Glama

browser_collect

Scrolls a list or table to accumulate visible rows with text-based deduplication, within limits and interruptible, without claiming full server-side completeness.

Instructions

Scroll a list/table and accumulate visible rows with text-based deduplication. Bounded and interruptible; never claims full server-side completeness. Leaves scroll position changed.

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": {
      "tabId": "<tabId>"
    },
    "name": "browser_collect"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoElement ref from the latest snapshot in this document.
tabIdYesTab id from browser_tabs.
browserNoBrowser id from browser_list, or chrome/firefox when only one instance matches.
frameIdNoFrame id from browser_frames; defaults to top frame.
maxItemsNo
maxStepsNo
revisionNoReject if the DOM revision differs from the snapshot.
selectorNoCSS selector. Must identify exactly one element.
documentIdNoReject the action if this snapshot document has changed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does real work: it discloses that collection is bounded and interruptible, that results are not guaranteed complete server-side, and that the scroll position is left changed. The main remaining gap is that it does not say whether deduplication persists across separate calls or whether text-identical but distinct rows are dropped.

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?

Three compact clauses, front-loaded with the core action, then limits, then side effects. No filler sentences and nothing repeated.

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 9-parameter tool with no annotations and no output schema, the description covers limits and side effects but says nothing about what the accumulated result looks like (row shape, ordering, how dedup affects output) or how it interacts with snapshot/revision staleness. It is adequate to call the tool but not to predict its return value.

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 78%, so the schema already documents most parameters (ref, selector, revision, documentId, maxItems, maxSteps). The description adds only the vague notion of being 'bounded' without tying it to maxItems/maxSteps or explaining tradeoffs between them, so it adds little beyond the schema.

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?

The description gives a concrete verb and resource: scroll a list/table and accumulate visible rows with text-based deduplication. That distinguishes it in spirit from the plain sibling browser_scroll, though it never names that sibling explicitly, so the differentiation is inferential rather than stated.

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?

Usage is only implied: an agent can infer this is the tool for harvesting rows from a scrollable list rather than moving the viewport. There is no explicit 'use this instead of browser_scroll / browser_snapshot when...' guidance and no stated preconditions such as needing a snapshot ref first.

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