Skip to main content
Glama

check_my_agent

Read-onlyIdempotent

Free, no key. Check a public MCP server by what an agent reads first: does it answer initialize and tools/list without a key, a current protocol version, instructions, a description for every tool, a type and a description for every parameter, a guide at /llms.txt. Returns a score of 100, a grade A to F, and for each missing point how to fix it. For your own server or your principal's; nothing of it is stored. PazAIr's own list, not a certificate or a security audit.

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": {
      "url": "<url>"
    },
    "name": "check_my_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe https address of the MCP endpoint, e.g. https://example.com/mcp. Public host names only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, idempotentHint=true), so the description focuses on value-add: no key or cost, nothing is stored, and the assessment is a heuristic list rather than a certificate or audit. One tension worth noting: it necessarily contacts arbitrary public hosts, while openWorldHint is declared false — the description implies broader reach than that annotation suggests.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The useful facts are front-loaded ('Free, no key', what is checked, what is returned, what it is not), but the first sentence is a long run-on enumeration of seven checks joined by commas, which slows scanning. The disclaimer tail earns its place; the checklist could be compressed.

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 takes on the burden of explaining returns and does so (score out of 100, letter grade, per-missing-point remediation) plus the no-storage guarantee. It leaves some practical gaps — behavior on auth-protected or non-MCP endpoints, and how long the check takes — but is otherwise adequate for a single-parameter, read-only diagnostic.

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 a single parameter with 100% schema description coverage, so the schema already carries the semantics (https MCP endpoint, example URL, public hosts only). The description repeats the 'public host names only' constraint without adding format or validation detail beyond the schema, matching the baseline-3 case for high coverage.

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 names a concrete verb and resource: check a public MCP server against a specific list of agent-facing criteria (initialize, tools/list, protocol version, instructions, tool/param descriptions, /llms.txt). It also states the return shape (score of 100, grade A–F, fixes). It is specific enough to distinguish from every sibling (register_agent, verify_receipt, use_tool), though the purpose is embedded in a long enumerative clause rather than stated crisply up front.

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?

Scope is bounded explicitly: 'For your own server or your principal's' and 'Public host names only', with when-not clauses ('not a certificate or a security audit'). No alternative sibling performs this function, so there is no alternative to route to, but there is also no explicit 'use this when…' trigger sentence.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources