Skip to main content
Glama

ExchangeRebel — pay-per-call APIs for AI agents (x402 on Solana)

sdk_safety_criteria

The published criteria for the SDK Safety service (sdk-version-safety/v1): the input contract, the per-flaw outcome states, the overall verdict rules including NOT-IN-RECORD, the honesty boundary, and the pinned public test corpus identity. Read these before paying - every report is reproducible from them. - no payment required: call directly without payment (no x402 challenge; this tool is free). HTTP equivalent: GET https://exchangerebel.com/toll/sdk-safety/criteria.

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": "sdk_safety_criteria"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

With no annotations provided, the description carries the behavioral burden well: it discloses that the call is free with no x402 challenge, that it is a read-style retrieval (HTTP equivalent GET), and that reports derived from these criteria are reproducible. It omits the response format/size of the criteria document, which is the main remaining behavioral gap.

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?

The description is front-loaded with what the document contains and then appends the actionable payment and HTTP-equivalent facts. The content enumeration is dense but each item is substantive; nothing is obviously padded, though the bullet-style appendage reads slightly tacked on.

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 zero-parameter document-retrieval tool with no output schema, the description tells an agent what the document covers and why it matters (reproducibility, pre-payment reading). Missing only the return format and whether the criteria are version-pinned/stable across calls, which would fully close the gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline of 4 applies; there is no parameter meaning to convey and the description correctly focuses on the returned content instead.

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 specific resource — the published criteria document for the SDK Safety service (sdk-version-safety/v1) — and enumerates its contents (input contract, per-flaw outcome states, verdict rules including NOT-IN-RECORD, honesty boundary, pinned test corpus identity). It does not explicitly name the sibling tools sdk_safety_check and sdk_safety_precheck, so differentiation is left implicit through the criteria/check/precheck naming pattern and the 'read before paying' framing.

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?

'Read these before paying' gives a clear sequencing rule: fetch this document prior to invoking the paid SDK safety check. It stops short of explicitly naming the alternative tool or stating when not to read the criteria, but the intent for an agent is unambiguous.

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