Skip to main content
Glama
Sign In

Feegate AI Agent data marketplace catalog & platform metrics

by org.feegate
OverviewDiscussionsAdmin

approval-audit.approval_risk

Read-onlyIdempotent

Ask "is this token approval dangerous" — full: every risk tag with reason and revoke guidance. ｜ 完整报告：全部风险标（no_approval / unlimited_allowance / large_allowance / spender_is_eoa / spender_flagged）、spender 命中的风险类别、代币精度、撤销调用示例与口径边界。参数同左。

[zh] 供应方资产「授权额度与 spender 风险」按次计费 $0.08 USDC（或等值积分）。 入参：owner、token、spender、chain。 [en] Vendor asset "授权额度与 spender 风险". Paid per call: $0.08 USDC (or prepaid credits). Args: owner, token, spender, chain. 付款/支付头在 MCP 请求头里带（X-Payment / X-Payment-Tx / Authorization: Bearer fg_…），不要放进参数。

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": {
      "owner": "<owner>",
      "token": "<token>",
      "spender": "<spender>"
    },
    "name": "approval-audit.approval_risk"
  }
}

Input Schema

NameRequiredDescriptionDefault
chainNo
ownerYes
tokenYes
spenderYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds material context beyond them: per-call pricing ($0.08 USDC or credits) and the requirement that payment proof travel in MCP headers (X-Payment / X-Payment-Tx / Bearer), not in parameters. It also previews what the response contains (tags, reasons, revoke call samples, scope boundaries). It does not cover failure modes such as unpaid-request behavior.

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

Conciseness2/5

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

The same content is delivered twice in Chinese and English with a garbled '｜' separator, a stray quotation mark in '"is this token approval dangerous', and a dangling cross-reference fragment. The useful pricing/header guidance is buried at the bottom instead of front-loaded.

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 a paid read-only audit with no output schema, the description does convey the return shape (risk tags, reasons, revoke example) and the payment mechanism, which is the most critical missing piece. It remains incomplete on parameter formats and on what happens when payment is absent or the approval does not exist.

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 had to carry parameter meaning, but it only restates the names 'owner、token、spender、chain' with no format guidance (e.g., chain name vs id, address casing, whether chain is optional with a default). The '参数同左' reference is meaningless outside the vendor's own docs.

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 opening line states a concrete question the tool answers ('is this token approval dangerous') and enumerates the exact risk tags returned plus revoke guidance, which is a specific verb+resource. The word 'full' hints at a more complete variant of a sibling, but no sibling is named, so differentiation is only implied.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance against alternatives such as allowance_check or address-risk tools. The fragment '参数同左' ('parameters as on the left') points at another tool's documentation rather than the caller's context, which is unhelpful rather than guiding.

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

All Feegate AI Agent data marketplace catalog & platform metrics toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources