Tutorial AI

Save document

save_document

Destructive

Save approved document HTML to the project. Creates a document when none exists; otherwise replaces the saved document. Call get_document first when replacing an existing document, show the exact title and HTML to the user, and wait for approval before calling this tool.

Input Schema

Name	Required	Description
`title`	No
`content`	Yes	Approved HTML to save.
`projectUid`	Yes

Output Schema

Name	Required	Description	Default
`created`	Yes
`document`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 30, 2026
- removedOutput schema / properties / document / properties / createdAt / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / document / properties / createdAt / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / document / properties / updatedAt / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / document / properties / updatedAt / type
```
Added value: +[
+  "string",
+  "null"
+]
```
First observedOct 15, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations declare destructiveHint=true and idempotentHint=false, and the description corroborates this by saying the tool 'replaces the saved document' and requires user approval of exact title and HTML before the call. It does not spell out what prior content is discarded or whether prior versions are recoverable, which is the main remaining gap.

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 sentences, no filler, front-loaded with the verb and create/replace semantics, followed by the required pre-call workflow. Each sentence carries a distinct, actionable fact.

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?

An output schema exists, so the description does not need to explain return values, and annotations cover the safety profile. The approval workflow is fully described; only the handling of pre-existing content and the role of projectUid remain underspecified.

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 only 33%, so the description has to compensate. It adds meaning for title (show the exact title to the user) and content (approved HTML), but projectUid has no semantics in either the schema or the description, leaving one of three parameters opaque.

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 states a specific verb and resource ('Save approved document HTML to the project') and disambiguates the create-vs-replace behavior in the same breath. An agent can separate this from generate_document and get_document without opening any schema.

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?

Explicitly states the pre-call protocol: call get_document first when replacing, show the exact title and HTML to the user, and wait for approval. This is a concrete when-to-use/how-to-use rule rather than an implied one.

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

All Tutorial AI 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?