Skip to main content
Glama

Discover Webmcp Tools

discover_webmcp_tools
Idempotent

Passively inventories page-registered WebMCP tools and returns complete input-schema summaries via the CDP WebMCP domain without registering or invoking them.

Instructions

Passively inventory every page-registered WebMCP tool and its complete structural input-schema summary using the experimental CDP WebMCP domain. Metadata is page-declared-untrusted; REA never registers or invokes discovered tools.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "target_id": "TARGET_ID_FROM_LIST_BROWSER_TARGETS",
      "cdp_endpoint": "http://127.0.0.1:9222",
      "observation_ms": 100
    },
    "name": "discover_webmcp_tools"
  }
}

Input Schema

NameRequiredDescriptionDefault
target_idYesExact CDP target identifier selected from the endpoint's target listing.
cdp_endpointYesLiteral loopback Chrome DevTools Protocol endpoint.
observation_msNo
allowed_originsNo

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?

Adds real context beyond the annotations: the operation is passive, results are page-declared-untrusted, the CDP WebMCP domain is experimental, and the tool will not register or invoke anything it finds. That last clause is the most valuable behavioral disclosure. However, it never reconciles the passive framing with readOnlyHint=false, so an agent cannot tell whether the CDP domain activation or observation window mutates browser state.

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, front-loaded with the action and mechanism, followed by the trust and side-effect caveat. Dense but every clause carries information; no filler.

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 an open-world, experimental-CDP discovery tool with four parameters and no output schema, the description covers what is returned (tool list with schema summaries) and the trust model, but leaves the observation window and origin allowance unexplained. The gaps in parameter meaning keep it at minimum-viable rather than complete.

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 50%: target_id and cdp_endpoint are documented, but observation_ms and allowed_origins have no descriptions anywhere. The description mentions no parameters at all, so it does not compensate — the observation window length and origin scoping are behaviorally significant and left entirely to inference.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: passively inventory every page-registered WebMCP tool plus its structural input-schema summary, via the experimental CDP WebMCP domain. This is specific enough that an agent can distinguish it from the binary/web-analysis siblings without opening the schema.

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 implied rather than stated: you use it when you want to enumerate page-declared WebMCP tools over CDP. There is a useful exclusion (REA never registers or invokes discovered tools), but no explicit when-not guidance, no mention of alternatives for enumerating page capabilities, and no statement of the prerequisite that a target must first be selected from the endpoint's target listing (that detail lives only in the schema).

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

Deploy Server

Other Tools