Skip to main content
Glama

browser_diagnostics

Read-onlyIdempotent

Inspect recent browser console errors, uncaught exceptions, HTTP errors, and failed requests to diagnose page failures; optionally clear diagnostic history.

Instructions

Inspect recent browser console errors, uncaught exceptions, HTTP errors and failed requests. Optional clear resets diagnostic history.

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": "browser_diagnostics"
  }
}

Input Schema

NameRequiredDescriptionDefault
clearNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.2/5.0
Behavior2/5

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

The description usefully discloses that clear resets/shreds diagnostic history, which is real behavioral context. However, this directly conflicts with the supplied annotations declaring readOnlyHint=true and destructiveHint=false, so the agent receives contradictory signals about whether the call can destroy state. The description also leaves 'recent' undefined (time window or count) and says nothing about what the inspection returns.

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?

Two tight sentences with no filler, and the primary read behavior is front-loaded ahead of the optional flag. Slightly short of ideal because the vague term 'recent' is doing load-bearing work that a concrete window or count would have handled without extra length.

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?

There is no output schema, so the description bears responsibility for signaling what comes back (error entries, counts, URLs, timestamps) and it does not. Combined with the undefined 'recent' window and the unresolved tension between the destructive clear wording and the read-only annotations, an agent can pick this tool but cannot predict its result shape.

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?

There is one parameter with 0% schema description coverage, so the description has to carry the meaning, and it does explain that clear resets diagnostic history rather than merely being a flag. It does not clarify the interaction between inspecting and clearing (does the call return the errors before wiping them) or the default no-clear behavior, which is the detail an agent actually needs.

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 specific verb plus resource scope: 'Inspect recent browser console errors, uncaught exceptions, HTTP errors and failed requests.' That enumerates exactly which diagnostic signals are collected, which is far more useful than a generic 'get browser diagnostics'. It stops short of a 5 because it never contrasts itself with nearby siblings such as browser_status or browser_performance, so the agent must infer the boundary.

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: the tool is for diagnosing browser errors, so an agent can guess it should be called after a page interaction fails. The one guidance-like statement, 'Optional clear resets diagnostic history,' hints at when to set clear, but there is no explicit when-not, no prerequisite (e.g. must a page be open?), and no named alternative.

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