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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-obvious operational facts: a 5¢ per-call price, values rounded to the nearest 10, figures as at 30 June, and a caveat that these are modelled rather than measured estimates — all of which affect how an agent should present the numbers.

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 core purpose and the 'modelled estimates' qualifier are front-loaded, then coverage and pricing in short labelled blocks. Every line carries information, though the pointer to `/v1/datasets/population-projections-vic` and the repeated title add a little redundancy for an agent that only needs to call the tool.

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 lookup with a fully documented 4-parameter schema and no output schema, the definition supplies the geography, temporal extent, rounding convention, licence-to-interpret caveat and cost. The main omission is what the response actually looks like (row shape, one row per LGA-period, units), which an agent must discover by calling.

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%, with from/to formats, the exact field enumeration, and the lga_name example already documented in the schema. The description adds only the framing that there are 'five age bands' and points to the dataset endpoint for the full field list, which is marginal value over the schema. Baseline 3 applies where 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+resource: projected resident population for every Victorian council area, with explicit time coverage (2021 then every five years to 2036), age-band granularity, and geography (80 LGAs). The 'Victoria' scoping alone distinguishes it from the NSW and QLD projection siblings without needing to open either schema.

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 '**Modelled estimates.**' callout and the 2021–2036 date range implicitly tell an agent this is forward-looking modelled data rather than observed history, which is a useful selection signal against lga_population and suburbs_demographics_population_history. However, no alternative tool is named and there is no explicit when-not-to-use condition, so the agent must infer routing from the projection wording alone.

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