agent-embassy

Correct Copy

correct_copy

Idempotent

Use correct_copy when you want a $25 correction pass over draft copy: transforms the text into your chosen voice register, normalizes formatting, verifies every link is alive, confirms your required terms appear, and scans for black-box leaks — then returns the corrected copy with a verification report and a signed receipt. You pay for the pass, never the method. POST the tool inputs as JSON to paid_url with an x402 v2 PAYMENT-SIGNATURE header. See https://docs.cdp.coinbase.com/x402 Paid tool — $25.00, USDC on Base or Arbitrum One. Paid URL: https://aemb.pro/v1/copy/correct.

Input Schema

TableJSON Schema

Name	Required	Description
`draft`	Yes	The raw draft copy to correct (1-20000 chars)
`links`	No	HTTPS URLs the copy references; each is verified alive via HEAD (fallback GET), 8s timeout, redirects never followed (max 20)
`register`	Yes	Voice register: founder-notes, elite, force, or bright
`required_terms`	No	Terms that must appear in the final copy (max 20; each term max 100 chars; counted case-insensitively)
`idempotency_key`	Yes	Idempotency key: UUID v4, client-generated, one per logical request. Replaying the same key on this tool returns the original receipt — the action is not re-run, and the first request's receipt wins even if you resend different inputs. Published example keys are rejected. Keys are scoped per tool and per payer account: a key never returns another wallet's receipt.

Output Schema

TableJSON Schema

Name	Required	Description
`how`	Yes	How to pay: POST the tool inputs as JSON to paid_url with an x402 v2 PAYMENT-SIGNATURE header
`tool`	Yes	Tool name, e.g. verified_check
`asset`	Yes	Settlement asset
`price`	Yes	Exact price, e.g. "$0.15"
`networks`	Yes	EVM CAIP-2 network ids accepted
`paid_url`	Yes	x402-paid HTTPS URL to POST the tool inputs to
`facilitator`	Yes	x402 facilitator
`payment_required`	Yes	Always true: this MCP tool is a payment pointer; the tool itself is monetized via x402.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 4, 2026

changedInput schema / properties / register / description

Previous value: -"Voice register: founder-notes, elite, force, or bright-soft-junior"New value: +"Voice register: founder-notes, elite, force, or bright"

changedInput schema / properties / register / enum

Previous value: -[
-  "founder-notes",
-  "elite",
-  "force",
-  "bright-soft-junior"
-]New value: +[
+  "founder-notes",
+  "elite",
+  "force",
+  "bright"
+]

Changed2 schema fields changedSep 26, 2026

removedInput schema / properties / agent_wallet

Removed value: -{
-  "description": "Dev mode only: declares the account wallet (string, min 20 chars) when no x402 payment is present. Ignored in live mode — there the wallet is recovered from the verified payment authorization.",
-  "type": "string"
-}

changedInput schema / properties / idempotency_key / description

Previous value: -"Idempotency key: any non-empty string (a UUID is recommended; no format is enforced). Replaying the same key on this tool returns the original receipt — the action is not re-run, and the first request's receipt wins even if you resend different inputs. Keys are scoped per tool: the same key on another tool is unrelated."New value: +"Idempotency key: UUID v4, client-generated, one per logical request. Replaying the same key on this tool returns the original receipt — the action is not re-run, and the first request's receipt wins even if you resend different inputs. Published example keys are rejected. Keys are scoped per tool and per payer account: a key never returns another wallet's receipt."

Changed6 schema fields changedSep 24, 2026

changedInput schema / properties / agent_wallet / description

Previous value: -"dev mode only"New value: +"Dev mode only: declares the account wallet (string, min 20 chars) when no x402 payment is present. Ignored in live mode — there the wallet is recovered from the verified payment authorization."

addedInput schema / properties / draft / description

Added value: +"The raw draft copy to correct (1-20000 chars)"

addedInput schema / properties / idempotency_key / description

Added value: +"Idempotency key: any non-empty string (a UUID is recommended; no format is enforced). Replaying the same key on this tool returns the original receipt — the action is not re-run, and the first request's receipt wins even if you resend different inputs. Keys are scoped per tool: the same key on another tool is unrelated."

addedInput schema / properties / links / description

Added value: +"HTTPS URLs the copy references; each is verified alive via HEAD (fallback GET), 8s timeout, redirects never followed (max 20)"

addedInput schema / properties / register / description

Added value: +"Voice register: founder-notes, elite, force, or bright-soft-junior"

addedInput schema / properties / required_terms / description

Added value: +"Terms that must appear in the final copy (max 20; each term max 100 chars; counted case-insensitively)"

AddedSep 24, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations cover safety (readOnly=false, idempotent=true, destructive=false), but the description adds the crucial non-structured context: it is a paid tool at $25.00 in USDC on Base or Arbitrum One, requires an x402 v2 PAYMENT-SIGNATURE header POSTed to paid_url, and returns a verification report plus a signed receipt. This is rich operational detail beyond the annotations (minor tension with openWorldHint=false given external link checks, but not a real contradiction).

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?

Purpose and payment mechanics are front-loaded and each sentence is largely functional, but there is a marketing-flavored filler clause ('You pay for the pass, never the method') and the paid URL appears twice ('paid_url' and an explicit 'Paid URL'). Minor redundancy keeps it from a 5.

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 5 parameters, an enum, and an existing output schema, the description supplies everything needed to invoke it: payment flow, endpoint, required header, and the return shape. It omits no critical calling information, though it never mentions rate limits or the openWorld nuance of external link checks.

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 description coverage is 100%, so the schema already fully documents draft, links, register, required_terms, and idempotency_key. The description reinforces the intent (chosen register, verified links, required terms) but adds no syntax or format detail beyond the schema, which is the expected baseline-3 case.

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?

Names a specific verb (correct) and resource (draft copy) and enumerates the concrete sub-operations: voice-register transformation, formatting normalization, link liveness verification, required-term confirmation, and black-box leak scanning. No sibling among the agentid_*/compute_*/kit tools overlaps, so the purpose is unambiguously distinguishable.

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?

Opens with 'Use correct_copy when you want a $25 correction pass over draft copy,' giving clear context and a cost basis for selection. It does not state when-not-to-use or name an alternative, but no sibling tool competes for this task, so the omission is minor.

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

All agent-embassy tools Inspect

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.