tslink

Overview Schema Source Related Servers Discussions Admin

Preview an app recipe

recipe_plan

Read-onlyIdempotent

Preview a single-app recipe to review owner configuration, safety warnings, and existing service comparison before applying it; performs no writes.

Instructions

Preview a single-app recipe with owner configuration, safety warnings and existing service comparison; writes nothing. Use before recipe_apply. Discovery never proves app authentication.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	Optional service name override.
`tags`	No	Comma-separated tags.
`allow`	No	Comma-separated private HTTP identities.
`funnel`	No	PUBLIC INTERNET exposure: review app authentication with the owner first.
`health`	No
`target`	No	Optional loopback HTTP(S) target override; use the host port.
`ephemeral`	No
`recipe_id`	Yes	Recipe ID from recipe_list.
`funnel_ttl`	No	Relative lifetime (descending unique units w,d,h,m,s,ms,us,ns) or until <RFC3339\|YYYY-MM-DD\|YYYY-MM-DDTHH:MM>. Local unless offset given; DST gaps/folds require an offset. Minimum 1h. Presets: 1h, 8h, 24h, 3d, 7d. Default 24h; guest/public maximum defaults to 7d, configurable in durations.public_max. Never refused. Omission on add preserves an existing deadline.
`public_ack`	No	Required acknowledgement when funnel is true.
`control_url`	No
`preserve_host`	No	Override the recipe Host forwarding default; omitted uses recipe.preserve_host. False explicitly restores upstream Host rewriting.
`request_limits`	No
`no_auto_provision`	No
`no_daemon_install`	No
`force_unsafe_public`	No	DANGER: overrides never-public recipe policy, potentially exposing host control, code execution or secrets to everyone. Requires funnel and public_ack.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`next`	Yes
`action`	Yes
`recipe`	Yes
`applied`	Yes
`dry_run`	Yes
`service`	Yes
`warnings`	Yes
`requested`	Yes
`schema_version`	Yes
`catalog_version`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 19, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint/destructiveHint=false/idempotent, and "writes nothing" is consistent with them. The description adds genuine context beyond the annotations: what the preview surfaces (owner config, safety warnings, service comparison) and the warning that discovery never proves app authentication.

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?

Two tight sentences: purpose and preview contents first, then the usage directive and the authentication caveat. No filler, and the highest-value routing information is front-loaded.

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?

With an output schema present, return values need not be explained, and annotations cover the safety profile, so the description is largely complete for a read-only preview. The main remaining gap is parameter-level guidance for a 16-param tool at 63% coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description never mentions any of the 16 parameters, and with schema coverage at only 63% several parameters are undocumented in both places. The generic mention of "owner configuration" and "safety warnings" does not map to specific parameters like funnel, public_ack, or force_unsafe_public.

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 (preview) and resource (single-app recipe), enumerates what the preview contains (owner configuration, safety warnings, existing service comparison), and distinguishes itself from recipe_apply. An agent can tell this apart from recipe_apply/recipe_list without opening either schema.

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?

"Use before recipe_apply" is an explicit when-to-use directive that names the alternative sibling. There is no explicit when-not condition (e.g. when to just use recipe_list), so it stops short of a 5.

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