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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds the operational definition of the metric (months to clear) and the market interpretation, which is useful contextual behavior. However, it does not disclose other behavioral aspects such as return format, precision, or error handling (e.g., invalid suburb). With annotations present, the description adds some value beyond them but is not rich in behavioral caveats.

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 two sentences with no fluff: the first defines the metric, the second provides a key threshold. The core definition is front-loaded, making it immediately clear what the tool does. Every sentence earns its place; there is no redundant information.

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 tool with a single simple parameter, safety annotations, and no output schema, the description is nearly complete. It explains what the tool computes and how to interpret the result. It does not explicitly state the return format (e.g., a number representing months), but this is implied. The description also helps distinguish this metric from related siblings. Overall, it provides sufficient context for an agent to call it correctly and understand the response.

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 documentation coverage is 0% – the parameter suburb_name has no description in the schema. The tool description refers to 'the suburb's current sales rate,' which clarifies that the parameter is the suburb of interest, but it doesn't explicitly state that the parameter must be a valid suburb name or provide format guidance. This is some compensation for the missing schema description, but it is minimal given the parameter is self-explanatory. A baseline of 3 is appropriate since the description adds a little meaning beyond the schema but does not fully compensate for the lack of parameter documentation.

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 clearly states the metric computed: 'How many months the current for-sale stock would take to clear at the suburb's current sales rate.' This is a specific verb-object pair (compute months of supply) that is distinct from sibling tools like days_on_market or stock_on_market. It also provides an interpretive threshold ('Under 2 months is a seller's market'), which further clarifies the tool's purpose.

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 description gives an interpretation of the result (seller's market threshold), which implies it is used to gauge market tightness, but it does not explicitly state when to use this tool instead of other market metrics like suburbs_market_supply_pressure, suburbs_market_days_on_market, or suburbs_market_stock_on_market. No alternatives are named, and no exclusionary guidance is provided. The context (market balance) is only implied, not explicit.

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