Local MCP

Recipe Delete

recipe_delete

Destructive

Use this when the user wants to remove one of THEIR saved recipes/skills (the manifests under ~/.local/share/local-mcp/recipes). Destructive with a preview gate: the first call (without confirm) shows what would be deleted; call again with confirm=true to actually delete. Bundled starter recipes can't be deleted. To modify a recipe instead, recipe_save with the same name and overwrite: true replaces it.

Input Schema

Name	Required	Description
`name`	Yes	Recipe name (from recipe_list).
`confirm`	No	Must be true to actually delete. Without it, returns a preview.
`remember`	No	With confirm: true, also stop asking for this kind of action from now on. Only when the person said so ("don't ask again"). The person can revoke it in LMCP or with set_always_allowed.

Output Schema

Name	Required	Description
`name`	No
`status`	No	'preview' when confirm was not set.
`deleted`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 24, 2026

addedInput schema / properties / remember

Added value: +{
+  "description": "With confirm: true, also stop asking for this kind of action from now on. Only when the person said so (\"don't ask again\"). The person can revoke it in LMCP or with set_always_allowed.",
+  "type": "boolean"
+}

AddedJul 12, 2026

TDQS

A4.9/5.0

Behavior5/5

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

While `destructiveHint: true` is provided in annotations, the description adds critical behavioral nuances not captured by standard hints, specifically the mandatory two-call workflow (preview then delete) and the ownership restriction.

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?

The definition is perfectly sized and follows a logical flow: scope -> danger level -> operational mechanism (preview gate) -> limitations -> alternatives. Every sentence contributes crucial context.

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?

The definition is maximally complete. It covers the 'what' (delete), 'who' (user-owned files), 'how' (preview gate), and 'what if' (alternatives), leaving no critical operational questions unanswered.

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?

The description adds valuable semantics to the parameters beyond the 100% schema coverage. It explains the functional role of the 'confirm' flag (preview vs. actual delete) and provides specific behavioral guidance for the 'remember' flag.

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 defines the action (remove recipes/skills) and the target resource (user's saved recipes/manifest location). It also explicitly contrasts this tool with `recipe_save` for modification.

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?

It provides multiple usage guidelines: defining scope (user's saved recipes), restrictions (cannot delete bundled starter recipes), and usage flow (two-step preview gate). It also directs the user to the correct alternative (`recipe_save`).

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

All Local MCP 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.