Zovo Inflation Calculator

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description still adds substantive behavior: the exact output components (adjusted amount, both index values, cumulative inflation, average annual rate, buying-power change), the operable period window 1913-01 to the latest bundled month, and the rule that only the output is rounded to cents. That is real context the annotations cannot convey.

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?

The trigger conditions are front-loaded and the negative list closes the paragraph cleanly. The middle clause stacking several SEO-style phrasings ("us inflation calculator", "dollar inflation calculator", "buying power calculator", "consumer price index calculator") is somewhat padded but each still serves intent matching.

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 three-required-parameter tool with a full output schema needs coverage of inputs, bounds, period range, and exclusions — all present. Nothing an agent needs in order to call it correctly, or to know when not to call it, is missing.

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 100%, so the baseline is 3, but the description adds genuine meaning by stating accepted input formats (year or YYYY-MM), the dollar-amount ceiling with fractional cents, and the rounding contract. It is largely a restatement of the schema constraints rather than a 5-level elaboration, so it lands just above baseline.

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 names a specific verb and resource ("converts one US dollar amount between two periods with the published CPI-U index") and fixes the scope to US CPI-U. It never names the sibling inflation_table, so an agent must infer the boundary between a point-to-point conversion and a tabular listing, which keeps it 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?

It enumerates concrete user phrasings that should trigger the tool ("what is $100 worth today", "buying power calculator", "consumer price index calculator") and gives an explicit negative list: other countries, regional or core CPI, forecasts, financial advice. An agent has no ambiguity about when to route here versus declining.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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 behavior is covered. The description adds useful behavioral context beyond annotations: the bundled CPI-U series coverage from 1913 through the latest full year, the 120-year-per-call limit, and CSV download availability.

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?

The description is front-loaded with the primary use case, followed by data-source and range details, then explicit exclusions. It is dense but every sentence earns its place.

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 two-parameter read-only table tool with full schema coverage, annotations, and an output schema, the description is complete enough: it covers purpose, data source, range limits, CSV output, and exclusions.

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 100%, and both start_year and end_year already document their bounds and the 120-year/latest-full-year constraints. The description reinforces the range and multi-year nature but does not add substantial parameter semantics beyond the schema.

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 states a specific output: a year-by-year table of annual average CPI-U and yearly inflation rate, with CSV download. It also distinguishes the tool from its sibling by naming adjust_for_inflation as the alternative for single-amount conversion.

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?

It gives explicit when-to-use cases (consumer price index calculator, inflation rate calculator, cpi calculator across many years) and explicit when-not-to-use cases (single amount conversion, other countries, monthly percent changes, forecasts), naming the sibling tool for the single-amount case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.