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

With no annotations provided, the description carries the full burden. It voluntarily discloses that coverage and observation frequency vary and that well-covered suburbs extend back 20+ years, which warns the agent about irregular data. It also states this is raw history rather than a processed score, giving an important semantic about the returned data.

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 three clear short sentences; the first defines the output, the second flags coverage variability, and the third contrasts with precomputed/forecast outputs. Each sentence earns its place and the key differentiators are front-loaded.

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 one-parameter read with an output schema provided, the description sufficiently covers what the tool returns (raw median sale-price series), why interactions (20-year return), and what not to expect (forecasts/precomputed scores). It could add explicit format/unit caveats, but the output schema and simplicity of the parameter keep this at a solid 4.

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?

The single parameter suburb_name has no schema description (coverage 0%), and the description barely explains it: it only refers to 'the suburb' generically. It does not compensate for the parameter gap by explaining valid forms, required granularity, or how to resolve suburb names, so it fails to add value beyond the field name itself.

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 verb+resource: 'Full median sale-price observation history for the suburb.' It goes further by distinguishing the raw historical series from a precomputed 'consistent growth' score or a forecast, which separates it from siblings like suburbs_forecast_sale and suburbs_market_median_sale_price.

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 identifies the core use case explicitly: 'needed to calculate a stated 20-year return.' It also excludes likely alternatives ['not a precomputed score or a forecast'], giving the agent a clear decision point. However, it names no sibling tools and provides no explicit when-not-to-use scenario beyond the forecast/precomputed contrast.

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