plan_approveApproves proposed filing-plan rows only after the person confirms yes in chat, and leaves a link only when they choose it.
Approve plan rows ONLY after the person said yes in chat. leave_link only if they chose it.
| Name | Required | Description | Default |
|---|---|---|---|
| rows | No | ||
| plan_name | No | current | |
| leave_link | No |
Changes observed during successful MCP inspections.
v0.1.1Output schema / (root)Previous value: -{
- "properties": {
- "result": {
- "additionalProperties": {
- "type": "integer"
- },
- "title": "Result",
- "type": "object"
- }
- },
- "required": [
- "result"
- ],
- "title": "plan_approveOutput",
- "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=true. The description contributes a genuine behavioral constraint the annotations cannot convey: approval must follow explicit human consent, and the link is only left when chosen. It does not say what state change approval causes, whether it is reversible, or what happens to rows left out — gaps that matter for a destructive tool.
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 sentences, front-loaded with the permission gate ahead of the optional flag. The lowercase "leave_link" starting a sentence is sloppy, but nothing is padded and no sentence is wasted.
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?
A destructive, zero-required-parameter tool with no output schema and 0% parameter documentation needs more: which rows are affected by default, what approval changes, and how it differs from plan_apply. As written, an agent cannot safely call this beyond the consent rule.
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 carry the load, but it explains only that leave_link is conditional. It never says what rows selects (all rows when null?), what plan_name "current" means, or what an integer row refers to. Two of three parameters are opaque in both schema and description.
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?
"Approve plan rows" gives a verb and resource, but what approval actually does (mark ready, commit pending changes, unlock apply) is never stated, and the boundary with close sibling plan_apply is left ambiguous. An agent can guess the general area but cannot state precisely what this call does.
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 hard precondition "ONLY after the person said yes in chat" is an explicit when-to-use rule, and "leave_link only if they chose it" is a conditional-use rule. What's missing is any mention of alternatives such as plan_review or plan_apply, so the routing decision among the plan_* siblings is still inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.