lightbulb-mcp

Overview Schema Source Related Servers Discussions Admin

smokeball_get_file

Read-onlyIdempotent

Retrieve a Smokeball file through a governed connector using project and account references. This action reads the requested document with approved authority.

Instructions

Smokeball connector operation get_file (platform tool smokeball.get_file).

Routes only through the exact project/account governed connector authority.

Args: arguments: JSON string of arguments for the connector operation. project_id: Authenticated Project UUID. project_ref: Exact project correlation reference. connector_account_ref: Project-bound connector account alias. idempotency_key: Stable business-action identity. effect: Required and must be read; Spring verifies it. approval_ref: Approved platform task UUID when resuming a write.

Input Schema

TableJSON Schema

Name	Required	Default
`effect`	Yes
`arguments`	No	{}
`project_id`	No
`project_ref`	No
`approval_ref`	No
`idempotency_key`	No
`connector_account_ref`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv0.1.1Sep 7, 2026

addedInput schema / properties / approval_ref

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Approval Ref"
+}

addedInput schema / properties / connector_account_ref

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Connector Account Ref"
+}

addedInput schema / properties / effect

Added value: +{
+  "const": "read",
+  "title": "Effect",
+  "type": "string"
+}

addedInput schema / properties / idempotency_key

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Idempotency Key"
+}

addedInput schema / properties / project_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Project Id"
+}

addedInput schema / properties / project_ref

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Project Ref"
+}

addedInput schema / required
```
Added value: +[
+  "effect"
+]
```

First observedv0.1.0Jun 25, 2026

TDQS

C2.3/5.0

Behavior3/5

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

The annotations already establish readOnly, idempotent, and non-destructive behavior. The description adds some value by stating that effect must be 'read' and that Spring verifies it, plus the routing/governance constraint. However, it also includes an approval_ref note about 'resuming a write' that is confusing for a read-only tool and does not clarify whether the response contains file content or a reference.

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

Conciseness3/5

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

The description is relatively concise and uses a clear Args section, but the opening line is a near-tautology of the tool name and the approval_ref entry seems irrelevant to a read-only get_file call. It is structured and readable, yet contains boilerplate that does not earn its place.

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

Completeness2/5

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

Although an output schema exists and return values need not be described, the description omits essential operational details: what must go into the 'arguments' JSON string, what resource is being fetched, and when to choose this over related smokeball file tools. The generic connector-wrapper language leaves the agent without enough context to invoke the tool correctly.

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?

Schema description coverage is 0%, so the description carries the full burden for parameter meaning. It does list all parameters with short labels, but the most important one, 'arguments', is only described as a 'JSON string of arguments for the connector operation'—it does not say what fields the JSON must contain to identify the target file. An agent cannot construct a correct call based on this description alone.

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

Purpose2/5

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

The description merely restates the tool name as 'Smokeball connector operation `get_file`' and focuses on governance routing, not on what the tool actually does (retrieves a file's metadata? content? by what identifier?). It does not differentiate from sibling tools like smokeball_get_file_download_url or smokeball_list_files, so an agent still cannot tell what this operation returns or which file it acts on.

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 guidance on when to use this tool versus alternatives such as smokeball_get_file_download_url, smokeball_get_file_upload_url, or smokeball_list_files. The line about routing through the governed connector authority is a constraint, not a usage condition. No exclusions or decision criteria are provided.

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

Deploy Server