Skip to main content
Glama
mcp-protocol-conformance

mcp-protocol-conformance

runCapabilityIntrospection

Read-onlyIdempotent

Compares a target MCP server's advertised initialize capabilities with the tools, resources, and prompts it actually returns, revealing mismatches for conformance checks.

Instructions

Compare the capabilities the target advertises in initialize against what tools/list, resources/list, prompts/list actually return.

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": {
      "target": "<target>"
    },
    "name": "runCapabilityIntrospection"
  }
}

Input Schema

NameRequiredDescriptionDefault
targetYes
specVersionNo2025-06-18

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / target / anyOf
      Removed value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "args": {
      -        "items": {
      -          "type": "string"
      -        },
      -        "type": "array"
      -      },
      -      "cmd": {
      -        "minLength": 1,
      -        "type": "string"
      -      },
      -      "cwd": {
      -        "type": "string"
      -      },
      -      "env": {
      -        "additionalProperties": {
      -          "type": "string"
      -        },
      -        "type": "object"
      -      },
      -      "kind": {
      -        "const": "stdio",
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "kind",
      -      "cmd"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "headers": {
      -        "additionalProperties": {
      -          "type": "string"
      -        },
      -        "type": "object"
      -      },
      -      "kind": {
      -        "const": "http",
      -        "type": "string"
      -      },
      -      "url": {
      -        "format": "uri",
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "kind",
      -      "url"
      -    ],
      -    "type": "object"
      -  }
      -]
    • addedInput schema / properties / target / oneOf
      Added value: +[
      +  {
      +    "properties": {
      +      "args": {
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      },
      +      "cmd": {
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "cwd": {
      +        "type": "string"
      +      },
      +      "env": {
      +        "additionalProperties": {
      +          "type": "string"
      +        },
      +        "propertyNames": {
      +          "type": "string"
      +        },
      +        "type": "object"
      +      },
      +      "kind": {
      +        "const": "stdio",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "kind",
      +      "cmd"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "properties": {
      +      "headers": {
      +        "additionalProperties": {
      +          "type": "string"
      +        },
      +        "propertyNames": {
      +          "type": "string"
      +        },
      +        "type": "object"
      +      },
      +      "kind": {
      +        "const": "http",
      +        "type": "string"
      +      },
      +      "url": {
      +        "format": "uri",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "kind",
      +      "url"
      +    ],
      +    "type": "object"
      +  }
      +]
  2. First observedv0.2.1

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds real behavioral content beyond that by enumerating the four protocol surfaces being cross-checked. However, it does not disclose what the tool actually does with the target (spawn a subprocess for stdio, open an HTTP connection) or what happens on a mismatch, and that connection behavior sits in some tension with openWorldHint=false.

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?

One sentence, front-loaded with the verb and the comparison, with no filler or repetition. It is efficient, though arguably under-sized for a tool whose schema has two distinct target variants.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema and no annotations describing the result, yet the description never says what a report looks like, how mismatches are surfaced, or whether failures are returned as errors or as data. For a tool that connects to an arbitrary target and compares four protocol surfaces across four spec versions, this leaves significant gaps an agent must guess at.

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 0%, so the description must carry parameter meaning and it does not. It references 'the target' but never explains the stdio-versus-http target shapes, nor does it explain what `specVersion` controls or why the default 2025-06-18 matters for the initialize comparison. An agent must read the raw schema to know how to construct a target at all.

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 uses a specific verb ('Compare') and names both sides of the comparison: capabilities advertised in `initialize` versus what `tools/list`, `resources/list` and `prompts/list` actually return. That is enough to distinguish it from siblings like runToolSchemaValidation or runAnnotationsAudit, which validate a single surface rather than cross-checking declared versus actual capability. It stops short of explicitly naming those siblings as alternatives.

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: an agent can infer this is the tool for checking that a server's declared capabilities match reality. There is no statement of prerequisites (that the tool connects to, or spawns, the target), no when-not-to-use guidance, and no pointer to runFullSuite or the narrower sibling checks. Minimum viable.

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