Delete a saved factory plan without changing your world; use plan_log to undo the deletion if needed.
Delete a saved plan. Nothing in the world is touched, and plan_log can undo it.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| save | No | ||
| as_of | No | pin to one world state: a sav:… token from an earlier answer | |
| world | No | ||
| base_rev | No | the plan version you read; needed to change an existing plan |
Changes observed during successful MCP inspections.
Input schema / properties / as_ofAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "pin to one world state: a sav:… token from an earlier answer",
+ "title": "As Of"
+}Input schema / properties / base_revAdded value: +{
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "the plan version you read; needed to change an existing plan",
+ "title": "Base Rev"
+}v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses the operation is destructive ("Delete"), scopes the blast radius ("Nothing in the world is touched"), and discloses recoverability ("plan_log can undo it"). It stops short of covering failure cases such as a non-existent plan name.
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?
Two short, front-loaded sentences with zero filler; the verb and scope lead, and the reversibility note follows efficiently.
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 simple delete with no output schema, the scope and reversibility disclosure is adequate, but the presence of four optional parameters with only 40% schema coverage means the description leaves meaningful invocation gaps unaddressed.
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 coverage is only 40%, so the description must compensate and does not. The optional save, world, and base_rev parameters are undocumented in both places, and the description never explains that name identifies the plan or how as_of/base_rev affect the delete.
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?
States a specific verb+resource ("Delete a saved plan") that is immediately distinguishable from siblings like rename_plan, list_plans, and plan_log. However, it does not explicitly name the contrasting sibling or spell out the saved-plan vs. world-state distinction as a routing rule, keeping it just short of a 5.
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?
Usage context is implied rather than stated: mentioning that plan_log can undo it hints at recovery flow, but there is no explicit when-to-use or when-not-to-use guidance versus rename_plan or forgetting a factory. The agent must infer the intent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.