Australian CPI

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuine value beyond annotations: the All Groups CPI measure set, the base period (2011–12 = 100), the 8 capital cities enumerated, monthly/quarterly availability, and the source/licensing (ABS Cat. 6401.0, CC BY 4.0). No contradiction with annotations — 'Retrieve' aligns perfectly with readOnlyHint.

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?

Three front-loaded sentences with zero waste: purpose first, return values second, coverage/frequency/source third. Every clause earns its place — city lists and licensing are packed efficiently without bloat. Well under any reasonable length ceiling for a tool with 4 parameters.

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 read-only retrieval tool with 4 optional, well-documented parameters, an output schema, and full annotation coverage, nothing an agent needs to call it correctly is missing. The description covers what data comes back, where it covers, at what frequencies, in what measures, and from what source. Cross-parameter constraints (annual_change is monthly-only) are handled in both the schema and description.

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 each parameter's schema description is already rich: last_n explains the 1–60 range with year equivalences and default, region expands every enum value, measure defines all three options and notes the monthly-only constraint, and frequency documents the interaction with measure. The tool description mostly mirrors this content (measure types, frequencies), adding no significant new parameter meaning. Baseline 3 is correct since the schema does the heavy lifting.

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?

States a specific verb ('Retrieve'), a precise resource ('Australia Consumer Price Index (CPI) data from the ABS CPI dataset'), and the exact return values (All Groups CPI as annual change, index numbers, or period change). This clearly distinguishes it from sibling ABS tools like abs.economy.gdp, abs.economy.labour_force, and abs.economy.trade without needing any schema inspection.

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?

Provides clear context for when to invoke: the description scopes the tool unambiguously to Australian CPI with its geographic coverage (national 8-city average plus 8 capital cities) and frequencies. It names no alternatives explicitly (e.g., bls.macro.cpi for US CPI), but the 'Australian' and 'ABS Cat. 6401.0' framing makes the selection boundary obvious, so a strong exclusion statement is a nice-to-have rather than a gap.

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