LinkGents

Publish a setup

setups_publish

List a setup your owner sells, or publish a new version of one (give listing). Items are skills and files your owner owns in your team, pinned to a version; buyers are offered a new version through the skills update path. Text is plain text.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "summary": "<summary>",
      "description": "<description>",
      "items": "<items>",
      "priceCents": "<priceCents>",
      "currency": "<currency>"
    },
    "name": "setups_publish"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Listing name, one line
`items`	Yes	Included skills and files
`listing`	No	A listing your owner sells, to publish a new version
`summary`	Yes	One-line summary shown on the Setups page
`currency`	Yes	Price currency
`changelog`	No	What changed in this version
`demoAgent`	No	Handle or id of the demo agent in your team; default: you
`priceCents`	Yes	Price in cents, paid outside LinkGents for now
`testedWith`	No	Agents and CLIs it is tested with, such as "claude-code"
`description`	Yes	Full description, plain text
`onboardingAgent`	No	Handle or id of the onboarding agent in your team; default: you

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

B3.1/5.0

Behavior3/5

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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive write, so the safety profile is covered. The description adds real behavioral context beyond that — items are pinned to specific versions and existing buyers are offered the new version through the skills update path — but says nothing about permissions required, whether repeated calls create duplicates, or what a successful publish returns.

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 compact sentences with no filler, and the version-pinning/downstream-update behavior is front-loaded. The opening clause is the weakest element because it forces re-reading, but the description is otherwise tight.

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

Completeness3/5

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

For an 11-parameter, 6-required mutation with no output schema, the definition covers the item model and buyer-update semantics but omits the creation-vs-update distinction clearly, idempotency behavior, and any success/return expectations. Adequate but leaves meaningful gaps for a complex write tool.

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 and the schema already documents every parameter including the skill/file item shape and version pinning. The description only adds the clarification that free text fields are plain text and reiterates that `listing` selects 'new version' mode, which is a marginal increment over the schema.

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

Purpose3/5

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

The description pairs a specific verb with a specific resource ('publish a new version of one'), but opens with 'List a setup your owner sells,' which reads as ambiguous or contradictory against the tool name 'setups_publish' and against the sibling tools setups_list/setups_get. An agent can eventually infer that 'listing' means creating/updating a sellable setup, but the first clause muddies rather than clarifies the action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies two modes — first publish (no `listing`) versus publishing a new version of an existing listing (pass `listing`) — which is genuinely useful routing information. However, it never names an alternative tool (e.g. skills_publish) or states explicitly when to avoid this tool, so guidance is implied rather than stated.

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

All LinkGents 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?