plan_applyExecutes approved filing-plan rows to apply document organization, logging every change and keeping actions undoable; creates folders only when explicitly approved.
Execute approved rows (logged, undoable). create_folders only if the person approved them.
| Name | Required | Description | Default |
|---|---|---|---|
| plan_name | No | current | |
| create_folders | No |
Changes observed during successful MCP inspections.
v0.1.1Output schema / (root)Previous value: -{
- "properties": {
- "result": {
- "additionalProperties": true,
- "title": "Result",
- "type": "object"
- }
- },
- "required": [
- "result"
- ],
- "title": "plan_applyOutput",
- "type": "object"
-}New value: +nullv0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is partly covered. The description adds meaningful behavioral context: execution is logged and undoable, and folder creation is gated on explicit approval. It still does not spell out the exact scope of what may be changed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences, front-loads the core action, and has no filler. Both sentences add useful information: undoability/logging and the approval condition for folder creation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a destructive mutation tool with no output schema, the description is adequate but incomplete. Annotations cover the destructive/read-only profile and the description adds logged/undoable context, but it does not explain plan_name, what rows are executed, or what the caller should expect after execution.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate for both parameters. It provides a conditional rule for create_folders, which is useful, but says nothing about plan_name, leaving one of two parameters completely unexplained beyond its name and default.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: 'Execute approved rows.' Combined with the name plan_apply and the mention of create_folders, an agent can infer this applies an approved plan. It does not explicitly differentiate itself from sibling tools such as plan_approve or plan_review.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'approved rows' implies this should be used only after approval, and 'create_folders only if the person approved them' gives a conditional usage rule for one behavior. However, it does not explicitly say when to use this tool versus plan_approve, plan_review, or plan_check.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.