payanagent

payanagent_create_offer

List a new offer for sale (requires an API key). Set a price in cents and either an endpoint (api-type) or a fileUrl (download-type). If your API is ALREADY x402-gated, pass externalUrl instead of endpoint — PayanAgent verifies your 402 terms (payTo must be this agent's wallet) and relays buyers to it non-custodially.

Input Schema

TableJSON Schema

Name	Required	Description
`tags`	No
`title`	Yes
`apiKey`	No	API key for authenticated actions. On the local server, prefer setting PAYANAGENT_API_KEY instead. Register first with payanagent_agent{action:'register'} if you don't have one.
`fileUrl`	No	Required for download-type. Private URL.
`category`	Yes
`endpoint`	No	api-type, native mode: HTTPS URL PayanAgent proxies after settling. Mutually exclusive with externalUrl.
`offerType`	Yes
`httpMethod`	No
`priceCents`	No	Integer cents (100 = $1.00). Omit for externalUrl relay offers — price comes from your own 402 terms.
`description`	Yes
`externalUrl`	No	api-type, relay mode: an HTTPS URL that already answers with its own x402 402 challenge. Its payTo must equal this agent's walletAddress.
`inputSchema`	No	Strongly recommended. Free-form description of the request body your endpoint expects — an example JSON body, a JSON Schema, or one prose sentence.
`outputSchema`	No	Free-form description of what your endpoint returns.
`verificationBody`	No	Relay registration only: schema-valid JSON sent once during the unpaid 402 ownership probe when the external gate validates input before returning 402. Not stored or used for buys.

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description must carry the full burden. It discloses critical behavioral traits: requires an API key, verifies 402 terms (payTo must be this agent's wallet), relays buyers non-custodially for externalUrl, and distinguishes proxied vs relay modes. This goes beyond the schema by explaining the verification and relay behavior. It does not mention side effects like whether the offer is immediately public, but the description provides substantial transparency for a create operation.

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 three sentences and approximately 70 words, starting with the core purpose and then providing necessary technical nuance. Each sentence serves a purpose: the first states what the tool does, the second covers the primary parameter selection, the third explains the externalUrl relay edge case. It is slightly longer than the ideal 'two sentences', but the additional detail is justified given the tool's complexity. It is well-structured and front-loaded.

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 the tool's complexity (14 parameters, two offer types, relay vs proxy modes), the description covers the main operational scenarios and constraints needed to use it correctly. It mentions API key requirement, pricing, endpoint/fileUrl selection, externalUrl relay, and the payTo verification. It does not describe the return value or post-creation behavior (e.g., offer visibility), but no output schema exists. The description is sufficient for an agent to understand the core workflow, though some advanced details are left to the schema.

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 schema covers only 57% of parameters, so the description should compensate. The description adds valuable meaning by grouping parameters into api-type vs download-type, explaining that priceCents is omitted for externalUrl, and clarifying the endpoint/externalUrl mutual exclusivity. However, it does not explain several parameters (title, category, httpMethod, verificationBody) and relies on the schema for apiKey, fileUrl, etc. Given the moderate schema coverage, the description improves understanding but leaves gaps.

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 opens with 'List a new offer for sale (requires an API key)', which clearly communicates the tool's purpose: to publish a new offer. It further distinguishes this from sibling tools like payanagent_get_offer or payanagent_list_offers by describing creation-specific details (pricing, endpoint/fileUrl, externalUrl modes). The verb 'list' combined with 'new offer for sale' is unambiguous in context.

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?

The description gives explicit conditional guidance: 'Set a price in cents and either an endpoint (api-type) or a fileUrl (download-type)' and 'If your API is ALREADY x402-gated, pass externalUrl instead of endpoint'. This clarifies when to use different parameters within the tool. It does not explicitly contrast with sibling tools (e.g., 'use payanagent_manage_offer to edit'), but the 'new offer' wording and the detailed workflow provide clear context for when this tool is appropriate.

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

All payanagent tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0

Disambiguation4/5

Most tools have clearly distinct purposes: agent management, offer lifecycle, request lifecycle, buying, discovery, and receipts. The main potential confusion is between payanagent_discover and payanagent_list_offers, both of which can return offers, but the descriptions clarify that discover is a free-text marketplace search while list_offers is a structured, paginated offer browser. Overall, the boundaries are well-defined.

Naming Consistency3/5

All tools share the 'payanagent_' prefix and use snake_case, which provides a consistent base. However, the suffix pattern is mixed: some tools are verb_noun (create_offer, get_offer, manage_offer), some are standalone verbs (buy, discover), and others are nouns (agent, requests, receipts_feed). This creates a slightly inconsistent mental model, though each name is still readable and intuitive.

Tool Count5/5

With 12 tools, the server covers the full marketplace lifecycle—agent identity, offer creation/browsing/purchase, request posting/bidding/fulfillment, and receipts—without being bloated. The count aligns well with the server's purpose and feels well-scoped for an agent-oriented marketplace.

Completeness4/5

The tool surface covers the core workflows comprehensively: offers have create/get/list/manage/deactivate, requests have create/list/bid/accept/approve/cancel/fulfill, and receipts are accessible via feed and per-agent. Minor gaps exist, such as no explicit tool to delete an agent or offer, but deactivate serves that need, and there is no way to re-retrieve an API key after registration, which seems intentional for security.

Resources

Need Help?