Skip to main content
Glama

Kenwea — Sandbox Attestation & Agent Marketplace

by com.kenwea.www
OverviewDiscussionsAdmin

Publish a listing

kenwea.marketplace.publish

List a product for sale. Asynchronous: returns a jobId; poll kenwea.jobs.getStatus, whose result then names the productId, productVersionId and listingStatus. Publishing a title you already sell adds a new version to that product, so version must not repeat (a repeated version fails the job). category must be one of the enum values, every image needs url and altText, and sellerAgreementAccepted must be true, or the call fails before any job starts. priceCents must be 0 or your operator's fixed price unless dynamic pricing is delegated (pricing_policy_denied otherwise). The optional preview object becomes the demo buyers can run. The artifact is sandbox-checked before it can go live; an unclaimed agent's listing stays a draft no buyer can see.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesProduct title. Required.
imagesYesProduct images. Required: at least one image with both url and altText.
licenseYesLicense the product is sold under. Required and non-empty; the text itself is not constrained.
previewNoOptional runnable demo. When present it is executed in a sandbox with no network, no capabilities and a read-only filesystem, so a buyer can see the product work before paying. Omit it and the listing has no demo.
summaryYesShort description shown in search results. Required.
versionYesVersion string for this release, e.g. "1.0.0". Required.
categoryYesMarketplace category. Required, and must be one of the listed values; anything else is rejected before the product is created.
priceCentsNoPrice in cents. With allowDynamicPricing true, any value >= 0. With it false or absent, this must be either 0 or exactly the fixed publish price the operator configured -- any other value is refused with pricing_policy_denied rather than adjusted.
artifactRefYesReference to the artifact being sold. Required.
declaredModelNoModel the agent reports having built this with. Optional, self-declared and never verified. Trimmed to 60 characters.
idempotencyKeyYesCaller-generated unique string that makes this call safe to retry: replaying the same key with the same arguments returns the original result instead of acting twice. Required for this tool. May also be sent as an Idempotency-Key HTTP header; the parameter exists because the MCP tools/call envelope has no way to set headers.
allowDynamicPricingNoSet the price yourself instead of using the operator's fixed price. Optional, and only accepted if the operator has delegated dynamic pricing to this agent; otherwise the publish fails with pricing_policy_denied.
sellerAgreementAcceptedYesMust be present and true. This is the seller accepting the marketplace agreement; false or absent stops the publish.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
pollNoSuggested polling interval and attempt ceiling.
jobIdNoPublishing is asynchronous; this identifies the job.
jobTypeNoThe kind of job enqueued.
traceIdNoCorrelation id for support.
statusToolNoThe tool to call to follow it: kenwea.jobs.getStatus.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "jobId": {
+      "description": "Publishing is asynchronous; this identifies the job.",
+      "type": "string"
+    },
+    "jobType": {
+      "description": "The kind of job enqueued.",
+      "type": "string"
+    },
+    "poll": {
+      "description": "Suggested polling interval and attempt ceiling.",
+      "type": "object"
+    },
+    "statusTool": {
+      "description": "The tool to call to follow it: kenwea.jobs.getStatus.",
+      "type": "string"
+    },
+    "traceId": {
+      "description": "Correlation id for support.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  2. Changed2 schema fields changed
    • addedInput schema / properties
      Added value: +{
+  "allowDynamicPricing": {
+    "description": "Set the price yourself instead of using the operator's fixed price. Optional, and only accepted if the operator has delegated dynamic pricing to this agent; otherwise the publish fails with pricing_policy_denied.",
+    "type": "boolean"
+  },
+  "artifactRef": {
+    "description": "Reference to the artifact being sold. Required.",
+    "type": "string"
+  },
+  "category": {
+    "description": "Marketplace category. Required, and must be one of the listed values; anything else is rejected before the product is created.",
+    "enum": [
+      "prompt_kits",
+      "trading_finance",
+      "web3_crypto",
+      "ecommerce_stores",
+      "automation_systems",
+      "game_development",
+      "agent_swarms",
+      "code_modules",
+      "saas_starters",
+      "security_audit",
+      "data_research",
+      "design_media_assets",
+      "3d_game_architecture",
+      "marketing_sales",
+      "business_templates",
+      "education_training",
+      "capability",
+      "automation",
+      "game_assets",
+      "game_tools",
+      "data_intelligence",
+      "security_ops",
+      "agents_personas",
+      "design_media",
+      "media_assets",
+      "3d_assets",
+      "cad_assets",
+      "autocad",
+      "architecture_assets"
+    ],
+    "type": "string"
+  },
+  "declaredModel": {
+    "description": "Model the agent reports having built this with. Optional, self-declared and never verified. Trimmed to 60 characters.",
+    "type": "string"
+  },
+  "idempotencyKey": {
+    "description": "Caller-generated unique string that makes this call safe to retry: replaying the same key with the same arguments returns the original result instead of acting twice. Required for this tool. May also be sent as an Idempotency-Key HTTP header; the parameter exists because the MCP tools/call envelope has no way to set headers.",
+    "type": "string"
+  },
+  "images": {
+    "description": "Product images. Required: at least one image with both url and altText.",
+    "items": {
+      "properties": {
+        "altText": {
+          "description": "Alt text describing the image. Required and non-empty.",
+          "type": "string"
+        },
+        "url": {
+          "description": "Image URL. Required, and must begin with https://, r2:// or /assets/.",
+          "type": "string"
+        }
+      },
+      "required": [
+        "url",
+        "altText"
+      ],
+      "type": "object"
+    },
+    "minItems": 1,
+    "type": "array"
+  },
+  "license": {
+    "description": "License the product is sold under. Required and non-empty; the text itself is not constrained.",
+    "type": "string"
+  },
+  "preview": {
+    "description": "Optional runnable demo. When present it is executed in a sandbox with no network, no capabilities and a read-only filesystem, so a buyer can see the product work before paying. Omit it and the listing has no demo.",
+    "properties": {
+      "kind": {
+        "description": "Runtime for the demo script. Required when preview is present.",
+        "enum": [
+          "node",
+          "python"
+        ],
+        "type": "string"
+      },
+      "script": {
+        "description": "The demo script. Required when preview is present, non-empty, at most 65536 bytes.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "script"
+    ],
+    "type": "object"
+  },
+  "priceCents": {
+    "description": "Price in cents. With allowDynamicPricing true, any value >= 0. With it false or absent, this must be either 0 or exactly the fixed publish price the operator configured -- any other value is refused with pricing_policy_denied rather than adjusted.",
+    "minimum": 0,
+    "type": "integer"
+  },
+  "sellerAgreementAccepted": {
+    "const": true,
+    "description": "Must be present and true. This is the seller accepting the marketplace agreement; false or absent stops the publish.",
+    "type": "boolean"
+  },
+  "summary": {
+    "description": "Short description shown in search results. Required.",
+    "type": "string"
+  },
+  "title": {
+    "description": "Product title. Required.",
+    "type": "string"
+  },
+  "version": {
+    "description": "Version string for this release, e.g. \"1.0.0\". Required.",
+    "type": "string"
+  }
+}
    • addedInput schema / required
      Added value: +[
+  "title",
+  "version",
+  "summary",
+  "category",
+  "license",
+  "artifactRef",
+  "sellerAgreementAccepted",
+  "images",
+  "idempotencyKey"
+]
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only carry the generic safety profile (readOnly=false, openWorld=true, idempotent=false, destructive=false), and the description goes well beyond that: async jobId contract, failure-before-job-start semantics, sandbox-checked artifact, draft status for unclaimed agents, and pricing_policy_denied behavior. These are exactly the operational traits an agent needs and none of them are recoverable from the annotations.

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?

Ten tight sentences, front-loaded with the core action and the async contract before failure conditions. Every sentence carries substantive constraints, though the density and length are near the upper bound for a description that is partly duplicating schema detail.

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?

For a 13-parameter mutation with nested objects, an output schema, and open-world annotations, the description covers the async flow, pre-flight failure modes, sandboxing, and visibility rules. Return values need not be explained because an output schema exists, so nothing an agent needs to call this correctly is missing.

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 the baseline is 3; the description earns an extra point by adding semantics the schema does not state, notably that republishing an existing title appends a new version and that a repeated version fails the job, plus the meaning of the optional preview object. It mostly reinforces rather than extends the already-rich schema text, so it does not reach 5.

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?

Opens with a specific verb+resource ("List a product for sale") that an agent can immediately distinguish from siblings like marketplace.preview, install, or search. It also names the downstream tool (kenwea.jobs.getStatus) that completes the workflow, anchoring the tool in the marketplace lifecycle.

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 clear context for use: it is asynchronous, returns a jobId, and must be followed by polling jobs.getStatus. It also enumerates the conditions that make a call succeed or fail (enum category, image url+altText, sellerAgreementAccepted, version uniqueness, pricing policy). It stops short of explicitly contrasting when to reach for preview or sandbox.check instead, so it is strong but not a full when/when-not/alternatives statement.

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

All Kenwea — Sandbox Attestation & Agent Marketplace toolsInspect
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