Skip to main content
Glama

inspect_compact

Read-onlyIdempotent

List interactive elements, forms, and readable sections across frames and open Shadow DOM, capped by maxChars, to provide compact snapshots for browser automation.

Instructions

List interactive elements (with refs), forms or readable sections across frames and open Shadow DOM, capped at maxChars.

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": "inspect_compact"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNointeractive
boxesNoInclude element bounding boxes [box=x,y,w,h] in snapshot lines.
queryNoFilter elements matching regex or substring.
tabIdNo
maxCharsNo
savePathNoFile under cwd or TURBO_BROWSER_SAVE_ROOT.
selectorNo
onlyChangedNoOmit elements unchanged since the previous inspect_compact snapshot.
includeFramesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.1
    • changedInput schema / properties / savePath / description
      Previous value: -"Optional file path relative to cwd to save snapshot text."New value: +"File under cwd or TURBO_BROWSER_SAVE_ROOT."
  2. First observedv0.4.0

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower. The description does add real behavior beyond them: refs are emitted, cross-frame and open Shadow DOM traversal happens, and output is truncated at maxChars. It omits that output is a text snapshot and says nothing about savePath or onlyChanged diffing semantics.

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?

A single dense sentence with zero filler, and the core resource is front-loaded. The parenthetical "(with refs)" interrupts the enumeration of modes slightly, but nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 9 optional parameters, four modes, frame/shadow-DOM traversal, change-diffing and file-save behavior, and no output schema, one sentence is not enough. An agent cannot tell from the description when savePath is honored, what selector/query do relative to mode, or what onlyChanged compares against.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 44%, so the description should compensate for the undocumented parameters. It only explains maxChars; mode, query, selector, savePath, boxes, tabId, onlyChanged, and includeFrames get no meaning from the description (frames and shadow DOM coverage only implicitly touches includeFrames).

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 verb ("List") and enumerates the resources returned: interactive elements with refs, forms, readable sections. It also names the traversal scope ("across frames and open Shadow DOM") and the output cap. It never names a sibling such as extract_clean_text or capture_page, so differentiation is left to inference.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance and no alternative tool is named. The mode enum in the schema hints at use cases (interactive vs article) but the description does not explain which to pick or when this beats capture_page or extract_clean_text.

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