Skip to main content
Glama

fingers

by co.fingersai

agent_card_check

VERIFY ANOTHER AI AGENT before trusting or paying it. Fetches its A2A Agent Card (+ ERC-8004 on-chain identity proof) and checks the claims -- A2A does NOT verify card authenticity, so impersonation, card tampering, and tool-squatting are real. Reports what the agent claims (name, skills, endpoints, payment address, on-chain registration) and flags problems: unreachable card, brand-new domain, a payment wallet flagged for scam/drain, or a card/registration mismatch. The KYA-complement (they say the agent is authorized; fingers says it's who it claims + safe). Give the agent's domain or Agent Card URL.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agentYesthe other agent's domain or Agent Card URL (e.g. someagent.com)

TDQS

A4.1/5.0
Behavior4/5

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

No annotations provided, so the description carries the full burden. It discloses that A2A does not verify card authenticity, warns about impersonation/tampering, and lists specific flags (unreachable card, new domain, wallet flagged, mismatch). This is transparent about limitations and outputs, though it doesn't detail auth/error behavior.

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?

Somewhat long but front-loaded with the key action, then explains risks, outputs, and comparison. All sentences contribute, though the KYA-complement phrasing is slightly cryptic.

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 complex tool with no output schema, the description covers what the tool fetches, what it reports, and what problems it flags, along with the trust model. It lacks explicit return format/error handling, but overall quite complete.

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 coverage is 100%, so baseline 3. The description restates the parameter guidance ('Give the agent's domain or Agent Card URL') with an example, adding minimal value beyond schema.

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 opens with a clear verb ('VERIFY ANOTHER AI AGENT before trusting or paying it'), specifies the resource (A2A Agent Card + ERC-8004 identity proof), and distinguishes from generic verify/check siblings by focusing on agent cards and impersonation risks.

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?

States when to use (before trusting or paying an agent) and gives input format. Mentions KYA-complement, implying a counterpart tool, but does not explicitly name sibling tools or list exclusions, so it's not a 5.

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

All fingers toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation3/5

Many tools share the same core purpose (safety checks) differentiated mainly by chain or asset type, and descriptions are detailed enough to distinguish them most of the time. However, pairs like rug_check/rugcheck and deployer_check/deployer_reputation have overlapping purposes that could lead to misselection.

Naming Consistency3/5

Most tool names follow a lowercase snake_case pattern with clear descriptors, but there are notable exceptions like 'rugcheck', 'defillama', and 'verify'. Additionally, the 'rug_check' vs 'rugcheck' pair is an obvious naming inconsistency.

Tool Count2/5

44 tools is excessive for any server. Even for a broad security/due-diligence purpose, many tools (especially the robinhood_* series) are highly specialized and could be consolidated into fewer actions.

Completeness4/5

The tool surface is impressively comprehensive, covering token/NFT safety, transaction simulation, whale/address tracking, stock analysis, prediction markets, and project validation. Minor gaps exist (e.g., no ENS resolution or stock price history), but they are not critical for the server's core purpose.

Resources