Skip to main content
Glama

submit_intent

Submit a buyer's INTENT in their own words. Two things happen: (1) you get back the products across the VIA network that genuinely match it, from the full agentic matcher (it reads each product's data and reasons, it is not keyword search); and (2) the intent is BROADCAST live onto the network as an anonymised teaser (category + product type + one attribute only, never the raw text or any identity), so it appears on The Wire (app.getvia.xyz/wire) and sellers can respond. Use this when you are buying ON BEHALF of someone and want defined matches plus live broadcast. State the brief naturally, including any hard requirements ("raw selvedge denim, 32 waist", "first pressing on the Stiff label", "a gift of coffee"). Hard requirements are enforced (a product that fails one is excluded); broad briefs return on-category options. Returns matches with seller, price, a direct page_url, and the mcp_url to transact, plus broadcast:true and a door_url when the intent went live. For matching AND broadcast tied to a specific VIA buyer's saved taste and budget (and seller pitch-back), call submit_intent on that buyer's MCP (/buyers/{handle}/mcp) instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
briefYesWhat the buyer wants, in plain words, e.g. 'made in japan raw selvedge denim around 32 waist' or 'a gift of coffee for a family member'.
categoryNoCategory if you know it, e.g. 'apparel/denim', 'music/vinyl', 'food/coffee'.
reply_toNoWhere a seller can reach you about this brief: your own MCP url, or an email. STRONGLY RECOMMENDED. Without it a seller who pays to unlock your brief has no way to come back to you, so your brief is broadcast but unanswerable. Released only to sellers who have paid at the door, never in a public teaser.
budget_usdNoCeiling in USD, if there is one.
type_termsNoThe product type in plain nouns, e.g. ['jean','denim trouser'].
preferencesNoSoft preferences. Used for ranking, never to exclude.
requirementsNoHARD requirements. A product failing any one of these is excluded. Be strict: put anything negotiable in preferences instead.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Describes return values (matches, broadcast:true, door_url), enforcement of hard requirements, ranking with soft preferences, anonymised broadcast behavior. No annotations provided, so description carries full burden, which it largely meets. Could mention if operation is idempotent or rate limits, but not essential.

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?

Description is dense but not excessively long. Every sentence adds value. Could be better structured with line breaks or bullet points, but as a single paragraph it remains clear and organized.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 7 parameters, no output schema, and no annotations, the description covers behavior, return values, usage context, and parameter nuances comprehensively. Provides a complete picture for an AI agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description adds context beyond schema: explains 'reply_to' is strongly recommended for seller responses, distinguishes 'requirements' (exclusion) from 'preferences' (ranking), and clarifies 'brief' should be natural language.

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 states the tool submits a buyer's intent and performs matching and broadcast. It distinguishes from sibling tools by specifying when to use this generic version versus the buyer-specific MCP endpoint.

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?

Explicitly says 'Use this when you are buying ON BEHALF of someone and want defined matches plus live broadcast.' Also provides alternative: for buyer-specific taste and budget, use the buyer's MCP endpoint.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation4/5

Most tools have clearly distinct purposes (discovery, purchasing, negotiation, seller management, taste/intent). Some overlap exists, e.g., multiple ways to get product details, but descriptions clarify distinct use cases. A few tools like find_buyers and get_buyer_briefs might be confused at first glance but have different inputs.

Naming Consistency4/5

Tool names predominantly follow verb_noun pattern in snake_case, e.g., find_seller, buy_product, get_shipping_quote. The outlier is seller_mcp_url which starts with a noun instead of a verb, and negotiate is a bare verb but fits. Overall consistent with minor deviations.

Tool Count3/5

28 tools is on the high side for a single server, but the domain is complex (agentic commerce covering discovery, purchasing, negotiation, seller registration, etc.). The count is borderline heavy but reasonable for the breadth of functionality.

Completeness4/5

The tool set covers major aspects of agentic commerce: search, buying, negotiation, shipping, digital delivery, seller onboarding, and taste/intent. Missing features like order tracking or store updates are minor gaps; core workflows are well-supported.

Resources