LastList

Publish a recipe publicly

publish_recipe

Publish one of the user's own recipes to a PUBLIC web page anyone can open, or unpublish one that's already live.

This puts the recipe on the public internet under the user's name, so ALWAYS get explicit confirmation before publishing — say which recipe and that it will be publicly visible, and wait for a clear yes. Never publish as a side effect of some other request.

Only recipes the user wrote in LastList can be published. Catalog recipes and ones imported from another site are refused for copyright reasons. Call my_recipes first to see which ones qualify.

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": {
      "recipeId": "<recipeId>"
    },
    "name": "publish_recipe"
  }
}

Input Schema

Name	Required	Description	Default
`action`	No	'publish' (default) to make it public, 'unpublish' to take the page down.
`recipeId`	Yes	The recipeId from my_recipes.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 26, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only say it is not read-only and not destructive, which understates the real consequence. The description supplies the crucial context the annotations omit: the recipe becomes publicly visible on the open internet under the user's name, requires explicit confirmation, and has copyright-driven refusal cases.

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?

Front-loaded with the core action and its most important consequence (public visibility), then the confirmation protocol, then eligibility. Four short sentences, each carrying non-redundant information; nothing repeats the schema.

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?

A low-parameter but high-consequence mutation tool; the description covers the confirmation flow, eligibility prerequisites, and the alternative tooling. With no output schema, it doesn't say what comes back (e.g., a public URL) or how to verify unpublishing, which is a minor but real gap.

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 adds real constraint meaning to recipeId beyond the schema's length bounds — it must come from my_recipes and must be an original user recipe — and implicitly covers the publish/unpublish action. It stops short of describing the unpublish path's semantics.

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?

States a specific verb and resource ('publish one of the user's own recipes to a PUBLIC web page') and covers the reverse operation (unpublish). It also distinguishes this from mere saving/sharing by naming the visibility scope and the ownership restriction, so an agent can tell it apart from siblings like save_recipe or share_list.

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?

Explicit when-to-use rules: always confirm with the user first, never publish as a side effect, and call my_recipes first to check eligibility. It also names the exclusion condition (catalog/imported recipes are refused), which is exactly the kind of routing information an agent needs.

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

All LastList 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?