VIA Network: Agentic Commerce

negotiate

Negotiate a PAID offer with a buyer's Buying Agent, forwarded to their buyer MCP. This is the post-door step: submit a paid offer at the brief door first (POST /api/via/brief/[brief_id]/offer), then pass that brief_id, the offer's payment_tx_hash and the offer_token the door returned to you. There is no free pre-door pitch.

Input Schema

Name	Required	Description
`brief_id`	Yes	The brief you made a paid offer against.
`offer_text`	Yes	Your full pitch: what you are offering, terms, and price.
`offer_token`	No	The offer_token the door returned when you paid for this offer. Required unless you send payer_signature.
`buyer_mcp_url`	Yes	The buyer's mcp_url from a find_buyers result.
`payer_signature`	No	Instead of offer_token: an EIP-191 signature by the paying wallet over "VIA paid offer\nbrief: <brief_id>\npayment: <payment_tx_hash lower case>".
`payment_tx_hash`	Yes	The on-chain payment tx from your door offer.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 9, 2026

addedInput schema / properties / offer_token

Added value: +{
+  "description": "The offer_token the door returned when you paid for this offer. Required unless you send payer_signature.",
+  "maxLength": 200,
+  "type": "string"
+}

addedInput schema / properties / payer_signature

Added value: +{
+  "description": "Instead of offer_token: an EIP-191 signature by the paying wallet over \"VIA paid offer\\nbrief: <brief_id>\\npayment: <payment_tx_hash lower case>\".",
+  "maxLength": 200,
+  "type": "string"
+}

First observedJul 27, 2026

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 carries the full burden and does disclose the critical behavior: this is a paid, post-payment step, requiring an on-chain payment_tx_hash plus either an offer_token from the door or a payer_signature. What it omits is what happens after submission (synchronous reply, counter, or async), which is significant given there is no output schema.

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?

Three sentences with the core action front-loaded, then the prerequisite flow, then the exclusion. The endpoint URL is verbose but functional; little is wasted, though the phrasing is denser than it needs to be.

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 six parameters, no annotations and no output schema, the description does well on prerequisites, payment and auth. The remaining gap is outcome behavior after the negotiation call, which an agent would want before chaining this into submit_intent or accept_offer.

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 baseline is 3. The description does add relational meaning by tying brief_id, payment_tx_hash and offer_token together as outputs of the same door-offer flow, but this largely restates what the schema property descriptions already say.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Negotiate a PAID offer with a buyer's Buying Agent'), scopes it as paid, and identifies the delivery channel (the buyer's MCP). It implicitly differentiates from free-pitch siblings via the 'no free pre-door pitch' line, but never names a sibling tool directly, so an agent still has to infer routing against tools like accept_offer or counter_quote.

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?

It states the exact precondition ('submit a paid offer at the brief door first, POST /api/via/brief/[brief_id]/offer, then pass that brief_id, payment_tx_hash and offer_token'), and adds an explicit exclusion ('There is no free pre-door pitch'). When-to-use, sequencing, and a when-not are all present.

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

All VIA Network: Agentic Commerce 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.

Resources

Need Help?