Underlayer

Update course

update_course

DestructiveIdempotent

Partially updates a course by id. Every field besides id is optional — send only what changes. It cannot publish: a person publishes from the Underlayer dashboard after reviewing the course.

Input Schema

TableJSON Schema

Name	Required	Description
`id`	Yes	The course id, as returned by list_courses or create_course.
`title`	No	New course title. Omit to leave it unchanged.
`status`	No	Only 'draft', which takes the course out of circulation. Publishing is done by a person in the Underlayer dashboard, after reviewing the course, and is not available to assistants.
`screens`	No	Replaces the whole screens array; it is not merged screen by screen. To change one screen, prefer update_screen. Omit to leave screens unchanged.
`themeId`	No	Id of a theme in this workspace to assign; null removes the theme. Omit to leave it unchanged.
`direction`	No	Reading direction of the course: 'ltr' or 'rtl'. Omit to leave it unchanged.
`navigation`	No	'default' shows the player's Back/Continue row; 'hidden' removes it (and swipe) so button blocks move the learner on. Omit to leave it unchanged.
`passingScore`	No	Percentage (0-100) of graded blocks a learner must answer correctly to pass; null means any completion counts. Omit to leave it unchanged.
`quizFeedback`	No	When learners see whether an answer was right: 'deferred' (at the end) or 'immediate' (as they answer). Omit to leave it unchanged.
`certificateId`	No	Id of a certificate template in this workspace; null goes back to the built-in default design. Omit to leave it unchanged.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`id`	Yes
`title`	Yes
`status`	Yes
`screens`	Yes
`themeId`	Yes
`createdAt`	Yes
`direction`	Yes
`updatedAt`	Yes
`navigation`	Yes
`sourceKind`	Yes
`contentHash`	Yes
`customFonts`	Yes
`workspaceId`	Yes
`passingScore`	Yes
`quizFeedback`	Yes
`certificateId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 8, 2026

changedInput schema / properties / status / description

Previous value: -"'published' makes the course live to learners; 'draft' takes it out of circulation. Omit to leave it unchanged."New value: +"Only 'draft', which takes the course out of circulation. Publishing is done by a person in the Underlayer dashboard, after reviewing the course, and is not available to assistants."

changedInput schema / properties / status / enum

Previous value: -[
-  "draft",
-  "published"
-]New value: +[
+  "draft"
+]

First observedSep 26, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuine context (partial-update semantics and the no-publish constraint) but omits the most consequential destructive behavior — that 'screens' replaces the entire array rather than merging — which lives only in the schema. Adequate but incomplete over the annotation baseline.

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?

Three short sentences, each earning its place: identity/scope first, partial-update contract second, publishing exclusion third. Nothing redundant and the essential constraint 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?

For a mutation tool with full schema coverage, annotations covering safety, and an output schema, the description supplies the needed partial-update and publish-restriction context. The one notable gap is not flagging the destructive whole-array replacement of screens, but that is documented in the schema.

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 all ten parameters are already documented in the schema; baseline is 3. The description's 'every field besides id is optional — send only what changes' generalizes the omit-to-leave-unchanged convention and clarifies the status/publish restriction, but adds no field-level detail beyond the schema.

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

Purpose4/5

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

States a specific verb+resource ('Partially updates a course') and adds the key scope qualifier 'by id' plus partial-update semantics. An agent can distinguish it from create_course and update_screen by the course-level scope, though the description never names a sibling directly (the schema does mention update_screen).

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?

'Send only what changes' tells the agent how to call it minimally, and 'It cannot publish: a person publishes... from the Underlayer dashboard' gives a clear when-not for the status field. It stops short of naming the sibling to use for single-screen edits (update_screen appears only in the schema).

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

All Underlayer 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?