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

With readOnlyHint/openWorldHint/destructiveHint already supplied, the description still contributes real behaviour: the statistical-reliability floor that nullifies the score, the exact output keys with an example, and a 10-credit charge. That is more than the annotations convey, but the credit cost is stated without any warning about when it is consumed (e.g., on a null result).

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?

Front-loaded with the opportunity definition, then output shape, then constraints, then cost — a sensible ordering. The example output block overlaps somewhat with the preceding prose listing of returned fields, so it is slightly longer than strictly necessary, but nothing is filler.

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?

There is no output schema, so the description carries the return contract itself, and it does: named fields, an example payload, an interpretation of the score, and the null case. Combined with the required-location rule and the credit price, an agent has everything needed to call it and read the result correctly.

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 100%, so the baseline is 3, but the description earns an extra point by declaring a constraint the schema omits entirely — 'REQUIRED: at least one location' against a schema with zero required properties — and by restating the Maison/Appartement filter as optional-with-default.

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 and analysis ('Identify renovation opportunities') and then defines the exact population scored: pre-1975 buildings priced below the area median. It goes further by pinning down the sense of the score (0-100, higher = bigger discount + older stock), so an agent can distinguish it from neighbouring analytical tools like analyze_building_age_price_impact without opening a 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?

It gives clear operating context: at least one location parameter is mandatory, type_local is an optional narrowing filter, and results below 10 pre-1975 transactions return a null score. It does not, however, name or exclude any alternative tool, so an agent must infer for itself when this beats a general transaction search.

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