Skip to main content
Glama

OnchainDiligence

by com.onchaindiligence
OverviewDiscussionsAdmin

inspect_payment

Read-only

FREE. Pure deterministic inspection of a proposed payment against structured policy (amount/network/asset/recipient/resource) — no external evidence, no sanctions screening, no cryptographic signing, no receipt. Returns the same ALLOW / REQUIRE_APPROVAL / BLOCK decision semantics as POST /x402/preflight-payment for the deterministic checks alone, so a caller can sanity-check a proposal before deciding whether the paid preflight (adds optional sanctions evidence and a signed, independently-verifiable receipt, $0.01) is worth paying for. This result is NOT cryptographically attested and carries no receipt — receipt is always null.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYes
policyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / policy / properties / acknowledge_unconstrained
      Added value: +{
+  "description": "Required (true) if every constraint above is null/omitted, confirming that was intentional and not an accident.",
+  "type": "boolean"
+}
    • addedInput schema / properties / policy / properties / expected_payer
      Added value: +{
+  "description": "Frozen commitment to the wallet expected to authorize the eventual on-chain payment (D2.4 binding strength) — decision-neutral, or null.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
  2. Added

TDQS

A4.5/5.0
Behavior5/5

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

The description goes well beyond the readOnly/openWorld annotations: it discloses that the operation is free, purely deterministic, makes no external calls, performs no sanctions screening, does not cryptographically sign, returns no receipt, and that the receipt field is always null. This is rich, accurate behavioral context.

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 the most important facts (FREE, deterministic, no external evidence) and uses three sentences to cover purpose, comparison, and limitations. It is slightly repetitive about the missing receipt, but every sentence carries meaningful information.

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?

Given no output schema, the description clearly communicates the decision semantics and the absence of a receipt, which are the critical behavioral outputs. It does not specify the exact response shape or error behavior, but it is sufficiently complete for an agent to decide whether to invoke it and what to expect.

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?

The description mentions the key decision dimensions (amount, network, asset, recipient, resource) and refers to structured policy, but gives no concrete guidance on the policy fields, formats, or the acknowledge_unconstrained flag. Since schema description coverage is reported as 0%, the description only partially compensates for the missing parameter-level guidance, though the schema itself is detailed.

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 clearly identifies the tool as a free, deterministic inspection of a proposed payment against a policy, and names the exact decision semantics returned (ALLOW / REQUIRE_APPROVAL / BLOCK). It also distinguishes itself from the sibling preflight_payment by explicitly excluding external evidence, sanctions screening, signing, and receipts.

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

Usage Guidelines5/5

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

The description states precisely when to use this tool: to sanity-check a proposal before deciding whether the paid preflight is worth paying for. It names the alternative (POST /x402/preflight-payment / preflight_payment) and explains what the paid version adds, making the choice between siblings explicit.

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

All OnchainDiligence 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