The live public receipts feed (newest first) — every settlement is signed and backed by an on-chain tx. Pass receiptId to fetch a single receipt instead of the feed.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Feed size, 1..200 (default 50). | |
| receiptId | No | Fetch one receipt by id instead of the feed. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses that receipts are live, public, newest-first, and backed by on-chain transactions. This adds meaningful behavioral context beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences are efficiently front-loaded with the main purpose and a key behavioral note. Every word earns its place; no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple feed tool with two parameters and no output schema, the description covers the core aspects: live feed, ordering, on-chain backing, and dual mode. Could benefit from a brief note on the response format, but it's adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both parameters. The description adds value by clarifying that receiptId switches from feed to single receipt, complementing the schema's description of the parameter's role.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool provides a live public receipts feed (newest first) and also allows fetching a single receipt by ID. The verb 'feed' and resource 'receipts' are specific, and it distinguishes the two modes of operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description explains when to pass receiptId to fetch a single receipt instead of the feed, giving clear context. However, it does not explicitly distinguish this tool from sibling payanagent_agent_receipts or state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
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.
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.
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.
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.
