Skip to main content
Glama
Sign In

Chrome-Stats

by com.chrome-stats
OverviewDiscussionsAdmin

Search extension source code

search_source_code
Read-onlyIdempotent

Search inside published extension source code. Premium plans only. Coverage is limited: only the latest version of each extension is indexed, only .js and .json files under 500KB, excluding locale files, and only Chrome, Edge, and Firefox. Report a negative result as "not found in the indexed subset", never as proof the string is absent.

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": {
      "query": "<query>"
    },
    "name": "search_source_code"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoOptional: restrict the search to one extension id.
pageNo
queryYesLiteral string to find in source code.
platformNoStore to query: chrome (Chrome Web Store), edge (Microsoft Edge Add-ons), firefox (Firefox Add-ons), android (Google Play), or apple (Apple App Store). Defaults to chrome.chrome

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already cover the read-only/idempotent profile, yet the description adds substantial disclosure annotations do not carry: an entitlement gate (premium plans), a precise indexing envelope (latest version only, .js/.json under 500KB, locale files excluded), and an explicit interpretive rule for negative results. That is exactly the kind of behavioral context that prevents an agent from over-claiming a string is absent.

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?

Four tight sentences, front-loaded with the purpose, then the entitlement gate, then coverage limits, then the reporting caveat. No filler, and every clause modifies how the tool's output should be treated.

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?

With no output schema, the description could still say what a match looks like (snippet versus file path) and that results are paginated via the page parameter. Everything else an agent needs to call this correctly and interpret its results is present.

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

Parameters4/5

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

Schema coverage is 75%, so the baseline is 3, but the description earns above that by clarifying that only Chrome, Edge, and Firefox are indexed; this effectively corrects the schema's platform enum description, which misleadingly lists android and apple as accepted values. It adds no detail on query syntax (literal string) or page usage, which is already in 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?

States a specific verb and precisely scoped resource: 'Search inside published extension source code.' This is clearly distinguishable from the metadata-oriented siblings search_extensions and search, though no sibling is named explicitly. The description goes on to define exactly what 'source code' covers, sharpening the scope further.

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

Usage Guidelines4/5

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

Gives clear usage context: premium plans only, and the coverage envelope in which results are meaningful. It also tells the agent how to report a negative result, which is a real usage rule. It does not name an alternative tool for when the query is really about extension metadata rather than code, which keeps it below a 5.

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

All Chrome-Stats toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources