plan_reviewOpens a filing plan in your browser so you can review, tick, and approve rows before the AI proceeds.
Open the plan in the person's browser to tick and approve rows.
| Name | Required | Description | Default |
|---|---|---|---|
| plan_name | No | current |
Changes observed during successful MCP inspections.
v0.1.1Output schema / (root)Previous value: -{
- "properties": {
- "result": {
- "additionalProperties": {
- "type": "string"
- },
- "title": "Result",
- "type": "object"
- }
- },
- "required": [
- "result"
- ],
- "title": "plan_reviewOutput",
- "type": "object"
-}New value: +nullv0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is partly covered. The description usefully adds that this launches an interactive browser UI for a human to tick and approve rows, which annotations cannot convey. But it omits key behavior: whether the call blocks awaiting human action, what it returns, and whether approval mutates plan state.
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?
A single front-loaded sentence with no filler; the action comes first. It is efficient, though its brevity borders on under-specification rather than true conciseness.
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 tool that opens an interactive UI and implies human approval of row changes, there is no output schema and no description of what happens after invocation — blocking behavior, return value, or state effects. An agent cannot tell what to expect when this tool returns.
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% and the single plan_name parameter (default "current") is never mentioned in the description. The text says only "the plan," giving no hint of what plan_name accepts or what "current" means, so the description fails to compensate for the coverage gap.
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 gives a verb ("Open") and a target ("the plan in the person's browser") plus an intent ("tick and approve rows"), so the basic action is graspable. However, "plan" and "rows" are undefined domain terms and it never distinguishes itself from close siblings such as plan_show, plan_approve, or plan_apply, which an agent could easily confuse with this.
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?
There is no explicit when-to-use or when-not-to-use guidance, nor any named alternative. The human-in-the-loop framing only implies a review-before-approval context, leaving the agent to infer it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.