Skip to main content
Glama
Firefox Bridge

Firefox Bridge

by matrodrigs

firefox_inspect

Read-onlyIdempotent

Inspect an element's box, computed styles, and basic accessibility signals via a snapshot reference or CSS selector to diagnose layout and styling issues without exposing form values.

Instructions

Inspect an element box, computed styles and basic accessibility signals using current snapshotId/ref or a unique CSS selector. Requires debug access. Omits field values and raw HTML; does not execute supplied code.

Input Schema

NameRequiredDescriptionDefault
refNoElement reference returned by read_page.
tabIdYes
frameIdNo
selectorNoUnique CSS selector, including open shadow roots.
snapshotIdNoIdentifier from the latest page read.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description still adds real value: the debug-access prerequisite, the explicit omission of field values and raw HTML, and the guarantee that supplied code is not executed. It stops short of describing failure behavior when the element or selector match is missing.

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?

Two tight sentences: capability and addressing modes first, then constraints and exclusions. Every clause carries information an agent needs, with no redundant restatement of the schema or the annotations.

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 a read-only inspection tool with no output schema, enumerating the three returned categories plus the debug-access requirement is close to sufficient. Marginal gaps remain around element-not-found behavior and whether frameId must accompany tabId for iframe inspection.

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 coverage is 60%, so the description compensates for some of the gap by tying ref to the current snapshotId and presenting the selector as an alternative addressing mode. tabId and especially frameId carry no meaning beyond their bare types in either the schema or the description.

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 ("inspect") with three concrete resources: element box, computed styles, and basic accessibility signals. It implicitly distinguishes itself from firefox_read_page by being element-scoped and from firefox_click/fill by being read-only, but it never names a sibling, so the differentiation is inferred rather than explicit.

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?

Gives mode-selection guidance (use current snapshotId/ref or a unique CSS selector) and a prerequisite ("Requires debug access"), which is genuinely useful. However, it never states when to choose this over firefox_read_page or firefox_find, nor what to do when both a ref and a selector are available.

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