action1-mcp-server

Update a custom data source

action1_update_data_source

Destructive

Updates a custom data source by ID, letting you modify its name, columns, description, or script and preview changes before execution.

Instructions

Update a custom data source. Updates a custom data source specified by its ID. Perm: manage_data_sources.

Input Schema

Name	Required	Description
`body`	No	Request body (schema: DataSourcePayload)
`confirm`	No	Required to execute. Exact string "YES".
`dry_run`	No	Default true (preview). Set false to execute.
`data_source_id`	Yes	Provide a specific data source ID.

Output Schema

Name	Required	Description	Default
`id`	No
`name`	No
`self`	No
`tool`	No
`type`	No
`status`	No
`builtin`	No
`columns`	No
`dry_run`	No
`language`	No
`would_send`	No
`description`	No
`script_text`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedv0.6.0Oct 26, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / properties / body / properties

Added value: +{
+  "columns": {
+    "description": "A list of data source output columns.",
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "description": {
+    "description": "The data source description.",
+    "type": "string"
+  },
+  "language": {
+    "description": "The language for querying data.",
+    "enum": [
+      "PowerShell"
+    ],
+    "type": "string"
+  },
+  "name": {
+    "description": "The name of the data source.",
+    "type": "string"
+  },
+  "script_text": {
+    "description": "The script text.",
+    "type": "string"
+  },
+  "status": {
+    "description": "This parameter is currently deferred.",
+    "enum": [
+      "Published",
+      "Draft"
+    ],
+    "type": "string"
+  }
+}

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / additionalProperties
```
Previous value: -trueNew value: +{}
```
addedOutput schema / properties / builtin
```
Added value: +{}
```
addedOutput schema / properties / columns
```
Added value: +{}
```
addedOutput schema / properties / description
```
Added value: +{}
```
addedOutput schema / properties / dry_run
```
Added value: +{}
```
addedOutput schema / properties / id
```
Added value: +{}
```
addedOutput schema / properties / language
```
Added value: +{}
```
addedOutput schema / properties / name
```
Added value: +{}
```
addedOutput schema / properties / script_text
```
Added value: +{}
```
addedOutput schema / properties / self
```
Added value: +{}
```
addedOutput schema / properties / status
```
Added value: +{}
```
addedOutput schema / properties / tool
```
Added value: +{}
```
addedOutput schema / properties / type
```
Added value: +{}
```
addedOutput schema / properties / would_send
```
Added value: +{}
```

First observedv0.5.0Jun 27, 2026

TDQS

C2.9/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is covered. The description adds useful non-annotation context — the required 'manage_data_sources' permission — but never mentions the dry_run/confirm preview-execute flow, which is the single most important behavioral fact for a destructive update.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first two sentences are near-duplicates: 'Update a custom data source.' followed by 'Updates a custom data source specified by its ID.' One of them is pure waste, and the remaining permission note is tacked on as an abbreviation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists and schema coverage is complete, so return values and parameter meaning are handled elsewhere. What is missing is the confirmation/preview workflow and any note about partial-update semantics for the nested body object — expected detail for a destructive tool with four parameters.

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 the schema already explains data_source_id, confirm, dry_run and every body field. The description only echoes that the target is specified by ID, adding nothing new; baseline 3 applies.

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 and resource ('Update a custom data source') and names the ID-based targeting, so an agent knows it is a mutation on a single data source. It does not, however, differentiate itself from the many sibling update_* tools (update_script, update_setting, update_report) beyond the resource name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this vs. action1_create_data_source, action1_get_data_source, or action1_delete_data_source, nor any prerequisite context. The only hint an agent gets is the permission string, which is a gate, not guidance.

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

Deploy Server