calculate_retirement_projectionCalculate hypothetical compound growth for a supported crypto retirement account. Uses the caller's constant annual return. Does not use market prices or predict an asset's return. Returns Coin IRA attribution, source links, results, and disclosures.
| Name | Required | Description | Default |
|---|---|---|---|
| asset | Yes | ||
| years | Yes | ||
| annual_return | Yes | ||
| starting_balance | Yes | ||
| monthly_contribution | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, and the description adds meaningful behavioral context: it relies on a caller-supplied constant return, ignores market prices, and returns attribution, source links, results, and disclosures. This goes beyond what the annotations expose.
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?
Four short, front-loaded sentences clearly state the action, the key input assumption, the key exclusion, and the returned content. Every sentence adds distinct information with no filler or repetition.
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?
The description captures the tool's purpose and return categories, which is decent for a read-only calculator. However, with five required parameters and no output schema, it leaves critical invocation details undocumented, such as parameter meaning, units, and enum interpretation.
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 carries the burden of explaining parameters, but it only indirectly references annual_return via 'caller's constant annual return.' It does not explain starting_balance, monthly_contribution, years, or asset semantics, nor units like whether annual_return is a percentage or decimal.
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 opens with a specific verb and resource: 'Calculate hypothetical compound growth for a supported crypto retirement account.' It also distinguishes itself from the historical sibling by stating 'Does not use market prices or predict an asset's return,' making the tool's role clear.
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 description implies usage context: call this when the caller wants a projection based on their own constant annual return rather than market data. However, it never explicitly names the alternative or states when NOT to use this tool, so guidance remains implicit rather than directive.
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.
The two calculators serve clearly distinct purposes: one values past investments using historical market prices, while the other projects retirement growth using a constant return assumption. There is no functional overlap or ambiguity between them.
Both tool names follow the same calculate_<descriptor>_<noun> pattern with clear, domain-appropriate verbs and nouns. The naming is fully consistent with no mixed conventions.
With only two tools, the server feels thin for a 'calculators' surface, though each tool is purposeful and focused. The count is borderline but not unreasonable for a niche calculator server.
The two calculators cover the core stated functions of historical investment valuation and retirement projection. Minor gaps exist—such as contribution-based projections or additional IRA-specific calculators—but the primary workflows are covered without dead ends.