Skip to main content
Glama

a2a_agent_card

Validate A2A Agent Cards from a URL or inline JSON, or generate a compliant card from agent details and skills; flags v0.3 cards and checks interfaces, capabilities, security, and signatures.

Instructions

A2A Agent Card validator and generator (A2A 1.0, detects and flags v0.3 cards): supportedInterfaces, protocolBinding/protocolVersion, capabilities, media-type modes, skills, provider, security schemes/requirements, JWS signature structure. Validate by URL (fetches /.well-known/agent-card.json) or inline JSON; or mode=generate from name, description, endpoint and skills. Costs 0.002 USDC on Base per successful call (x402). Without a payment key this tool returns the 402 challenge.

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": "a2a_agent_card"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoAgent origin or card URL
cardNoInline Agent Card JSON (POST)
modeNovalidate (default) or generate
nameNogenerate: agent name
skillsNogenerate: JSON array or comma-separated skill names
endpointNogenerate: A2A endpoint https URL
descriptionNogenerate: description

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses outbound fetching of a well-known path, a per-successful-call cost of 0.002 USDC on Base via x402, and the 402 challenge returned without a payment key. That is exactly the kind of non-obvious behavior an agent needs; it stops short of describing the validation report or failure semantics for malformed cards.

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?

It is one dense paragraph, front-loaded with the tool's identity before the mode/payment details, and nearly every clause carries information (versions, checks, cost, 402). The long run of check categories is slightly list-like but still scannable.

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?

For a seven-parameter, annotation-free, no-output-schema tool, it covers the essential gaps: what it checks, how to invoke each mode, what it costs, and what happens without payment. Residual gaps are the shape of the validation result and behavior on invalid input, which an agent could still want.

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?

Schema description coverage is 100%, so the schema already documents all seven parameters and the description merely restates them. It does add a little meaning by clarifying that 'url' accepts an origin as well as a card URL and that mode defaults to validate, but that is marginal over the schema baseline.

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?

The description gives a concrete verb-plus-resource ('A2A Agent Card validator and generator') and even enumerates the aspects it checks (supportedInterfaces, protocolBinding, skills, security schemes, JWS signature). It also separates the two operating modes, so an agent knows exactly what it is getting without consulting 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 Guidelines4/5

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

It clearly routes usage: validate by URL (which fetches /.well-known/agent-card.json) or by inline JSON, versus mode=generate from name/description/endpoint/skills. That is explicit mode-selection guidance, though it does not address when to prefer this over a sibling like json_schema_validate or what happens if both url and card are supplied.

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