529 calculator
| Name | Required | Description | Default |
|---|---|---|---|
| years | Yes | ||
| currentBalance | Yes | ||
| expectedReturnPct | No | ||
| monthlyContribution | Yes | ||
| firstContributionDate | No | Optional date of the first monthly contribution, as YYYY-MM-DD. Adds firstContributionDate, lastContributionDate and targetDate (when the projected balance is reached). It only labels the plan; the amounts do not change. A day of 29 to 31 moves to the last day of shorter months. |
Changes observed during successful MCP inspections.
Input schema / properties / firstContributionDateAdded value: +{
+ "description": "Optional date of the first monthly contribution, as YYYY-MM-DD. Adds firstContributionDate, lastContributionDate and targetDate (when the projected balance is reached). It only labels the plan; the amounts do not change. A day of 29 to 31 moves to the last day of shorter months.",
+ "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description adds nothing beyond that — no note on defaults (expectedReturnPct has none), no statement that the projection is deterministic, no explanation of what the calculation returns.
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 words is trivially short but under-specified rather than concise — there is no front-loaded statement of what is computed or what the agent gets back. Brevity here is a deficit, not an efficiency.
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 five-parameter projection tool with no output schema and only 20% schema coverage needs the description to explain inputs, defaults, and the shape of the result. None of that is present, so an agent cannot call it reliably without guessing at expectedReturnPct and the return value.
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 only 20%: four of five parameters (years, currentBalance, monthlyContribution, expectedReturnPct) have no schema descriptions, and the description supplies no meaning for any of them. With this low coverage the description was obligated to explain units, defaults, and expectedReturnPct semantics, and it does not.
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 '529 calculator' restates the tool name and title ('Converters 529') without adding a verb, scope, or output statement. An agent can infer it projects a 529 education savings plan, but nothing distinguishes it from siblings like converters_college_cost or calculate_compound_interest.
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 statement of when to use this tool, when not to, or which sibling to prefer for overlapping goals (e.g., converters_college_cost, calculate_compound_interest). Every bit of routing must be inferred from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.