Zinvyl Marketplace Agent Gateway

Match a need or record unmet demand

match_or_capture_demand

Idempotent

Use when an agent has a sanitized business need but does not know whether Zinvyl sells it. Returns an existing fixed offer when one matches. Otherwise records privacy-minimized product-demand telemetry for owner review; it creates no order, quote, outreach, funding claim, or delivery commitment.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`source`	No	Optional allowlisted source where the agent discovered Zinvyl.
`industry`	No	Optional broad industry only; do not name a person or confidential project.
`budget_cents`	No	Optional buyer-stated total budget in USD cents. This is demand telemetry, not spending authority or proof of funds.
`category_hint`	No
`agent_tool_type`	No		mcp_client
`request_summary`	Yes	One sanitized business outcome. Do not include names, email addresses, phone numbers, credentials, payment data, personal data, confidential text, or production secrets.
`turnaround_days`	No	Optional requested turnaround in calendar days.
`requested_output`	No	Optional sanitized deliverable type, such as weekly report or data export.
`authorized_to_share`	Yes	True only when the requester is authorized to share this sanitized need with Zinvyl for matching and aggregate product planning.
`near_match_offer_id`	No	Optional closest offer; it does not place unsupported work in scope.
`contains_no_personal_data_or_secrets`	Yes	True only after removing personal data, credentials, confidential material, and payment data.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 8, 2026

changedInput schema / properties / near_match_offer_id / enum

Previous value: -[
-  "zinvyl.venture.evidence-brief.v1",
-  "zinvyl.venture.prototype-scope.v1",
-  "zinvyl.freight.workflow-audit.v1",
-  "zinvyl.api.workflow-failure-rescue.v1",
-  "zinvyl.api.failure-triage.v1",
-  "zinvyl.freight.full-workflow-audit.v1"
-]New value: +[
+  "zinvyl.venture.evidence-brief.v1",
+  "zinvyl.venture.prototype-scope.v1",
+  "zinvyl.freight.workflow-audit.v1",
+  "zinvyl.api.workflow-failure-rescue.v1",
+  "zinvyl.api.failure-triage.v1",
+  "zinvyl.freight.full-workflow-audit.v1",
+  "zinvyl.content.ai-marketing-pilot.v1"
+]

Changed5 schema fields changedOct 7, 2026

changedInput schema / properties / agent_tool_type / default
```
Previous value: -"unknown"New value: +"mcp_client"
```

changedInput schema / properties / near_match_offer_id / description

Previous value: -"Optional closest offer previously returned by list_offers; this does not imply the unsupported request is in scope."New value: +"Optional closest offer; it does not place unsupported work in scope."

removedInput schema / properties / source / default
```
Removed value: -"direct"
```

addedInput schema / properties / source / description

Added value: +"Optional allowlisted source where the agent discovered Zinvyl."

changedInput schema / properties / source / enum

Previous value: -[
-  "direct",
-  "toku",
-  "gohirehumans",
-  "toll_bench",
-  "callboard",
-  "agent_directory",
-  "mcp_registry",
-  "a2a_registry",
-  "other"
-]New value: +[
+  "direct",
+  "direct_agent",
+  "mcp_registry",
+  "a2a_registry",
+  "ai_agents_directory",
+  "toku",
+  "gohirehumans",
+  "toll_bench",
+  "callboard",
+  "recruiting_bot",
+  "peerpush",
+  "other"
+]

AddedOct 6, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations say readOnlyHint=false and idempotentHint=true, but the description adds crucial context: it records telemetry rather than creating transactions, and explicitly lists what commitments it does NOT create. This is genuinely useful behavior disclosure beyond what annotations convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight clauses: trigger, primary behavior, fallback behavior plus explicit non-commitments. No filler. Front-loaded with the use case.

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 11 params with 82% schema coverage and no output schema, the description supplies the essential missing context: this is a low-commitment telemetry write, not a purchase. An agent knows exactly when to call it and what not to expect from the response.

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 coverage is 82%, so the schema documents most parameters well, including the strict const booleans that gate sharing. The description doesn't add syntax or format details beyond the schema, and the 'sanitized' framing is already echoed in schema descriptions. Baseline 3 applies.

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 dual-purpose operation (match existing offer else record demand) and states what it does not do (no order, quote, outreach). Clearly distinguishable from siblings like find_service and buy_service.

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?

Opens with an explicit 'Use when' condition (sanitized need, unknown whether Zinvyl sells it), which distinguishes it from find_service (known request) and buy_service (commitment). The fallback behavior is specified inline.

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

All Zinvyl Marketplace Agent Gateway 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?