Consumer prices (CPI)

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

No annotations are supplied, so the description carries the full disclosure burden. It usefully conveys the unit semantics of each measure (% change vs index level) and the trimmed_mean preference, which is real behavioral value, but it says nothing about response shape, series granularity, or whether results are paginated/truncated.

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 dense sentences, front-loaded with the data source and immediately followed by the measure decision, then item selection, then the code-lookup fallback. No sentence is filler; each one corresponds to an actual decision the caller must make.

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 six-parameter read tool with no annotations and no output schema, the description covers the two hardest choices (measure and item) and points to the sibling needed for custom codes. Remaining gaps (city semantics, date-range behavior, return structure) are adequately handled by the schema itself, though the lack of any output-shape hint keeps it short of full completeness.

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 high (83%), so the baseline is 3, but the description adds meaning the schema lacks: it explains the otherwise-undocumented 'measure' enum in concrete terms and gives a worked item selection ('rents' for rent inflation) plus the escape hatch of raw ABS codes. The adjustment and city parameters are left to the schema, which already documents them.

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?

Names a specific resource (ABS monthly Consumer Price Index inflation) with its two axes of granularity (item and capital city), so an agent immediately knows this is the Australian CPI endpoint rather than any of the rate/labour-force siblings. The data source is explicit, leaving no ambiguity about what is returned.

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?

Explicitly routes the agent between the three measure values ('annual_change' for year-on-year inflation, 'monthly_change' for month-on-month, 'index' for price levels) and flags the RBA-preferred underlying measure (trimmed_mean). It also names the sibling tool abs_describe_dataflow for retrieving raw ABS index codes, which is exactly the kind of alternative-routing guidance that prevents misuse.

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