Skip to main content
Glama

SigLint — HTTP Message Signature Doctor

signcheck_verify

确定性体检一份 HTTP 消息签名样本(RFC 9421):逐项 checks 给出缺哪个头/覆盖组件够不够/content-digest 是否对得上/created 是否新鲜/签名能否用给定公钥验过,返回 verdict 与可兑现收据。按次计费,0.002 USD/call(demo 账本,仅联调);真实收款:19.00 CNY / 200 次提取码。先付后跑。

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": {
      "request": "<request>",
      "key_jwk": "<key_jwk>",
      "keyid": "<keyid>",
      "proof": "<proof>",
      "ts": "<ts>",
      "nonce": "<nonce>"
    },
    "name": "signcheck_verify"
  }
}

Input Schema

NameRequiredDescriptionDefault
tsYes
keyidYes已登记钥匙的 keyid(URL)
nonceYes
proofYes对 signcheck-mcp/v1|工具|参数摘要|ts|nonce 的 Ed25519 签名
key_jwkYes签名者的 Ed25519 公钥 {kty,crv,x}
max_ageNocreated 允许的最大年龄(秒)
paymentNoX-PAYMENT 同形:dict 或 base64url(JSON)
requestYes{method,url,headers,body_b64}
entitlementNosigncheck_redeem 发出的 AK(提款码换来的次数包);传了它就不用 payment

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / entitlement
      Added value: +{
      +  "description": "signcheck_redeem 发出的 AK(提款码换来的次数包);传了它就不用 payment",
      +  "type": "string"
      +}
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

With zero annotations, the description carries the whole burden and does disclose the crucial non-obvious trait: the tool is paywalled (0.002 USD/call demo ledger, 19.00 CNY per 200 credits live) and must be settled before execution, which an agent cannot infer from the schema. It also states the operation is deterministic and yields a verdict plus a redeemable receipt. It does not say whether credits are consumed on a failed verification, nor how errors surface.

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 capability statement is front-loaded and dense, with the checklist of validations doing real work. The trailing billing sentences are wordier than needed (demo ledger caveat plus a second live-pricing scheme) but do convey decision-relevant paywall information, so they largely earn their place.

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 9-parameter tool with a nested `request` object and no output schema, the description explains what the checks produce but describes the return only as "verdict 与可兑现收据", leaving the shape of the per-check results and the receipt unstated. The proof/nonce/keyid authentication flow is likewise left entirely to the schema, so the definition is workable but not complete for a call with this much surface.

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 78%, so the schema already documents most fields; the baseline is 3. The description does add meaning for a few of them by implication — "created 是否新鲜" maps to `max_age`, "给定公钥" maps to `key_jwk` — but it leaves `proof`, `nonce`, `keyid`, and `entitlement`-vs-`payment` selection to the 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 names a specific verb ("确定性体检") and a specific resource (an HTTP message signature sample, RFC 9421), then enumerates exactly what is checked: missing headers, covered-component sufficiency, content-digest match, `created` freshness, and public-key verification. This is clearly disjoint from signcheck_pricing (price lookup) and signcheck_redeem (voucher/entitlement redemption), so an agent can pick it without opening 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 Guidelines3/5

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

The description supplies a real precondition ("先付后跑" — pay before it runs) and the demo-versus-live price distinction, which tells the agent the call is gated. However, it never states when to use this instead of signcheck_pricing or signcheck_redeem, nor what to do if verification is not desired; usage must be inferred from the name.

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