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

Beyond the readOnly/openWorld annotations, it discloses data-quality behavior that materially affects how results are reported: counts reflect Cubi's inventory, not market size; values are asking prices, not sale prices or valuations, and must be labeled as such; places are resolved at the `level` reading; and no figure may be computed that is absent from the result. These are non-obvious constraints an agent could easily violate without the text.

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 prose is front-loaded — what it does, when to use it, how the numbers are computed, then the reporting caveats — and every sentence carries information. The Args block largely restates field descriptions already at 100% schema coverage, and the Returns section duplicates the output schema, which is a modest amount of redundancy in an otherwise tight definition.

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 an 8-parameter comparison tool with an output schema, the description covers the input contract, the cohort arithmetic, the meaning of share_pct, the sample `listings` payload used for 'show me those' follow-ups, and the caveats that keep the agent from overstating the data. Nothing essential for correct invocation or correct reporting is missing.

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 most parameter meaning is already structured, but the description adds the 2-3 place cardinality limit (absent from the schema, which has no minItems/maxItems) and explains how the parameters compose into cohorts: within `max_price`, then optionally filtered by `has_parking` mention, with `share_pct` defined as that part over the priced cohort. That composition logic is not derivable from the individual field descriptions alone.

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 names a specific operation — counting, for each of 2-3 places, the share of active listings within a price cap and optionally with parking. A reader can distinguish it from listing-search tools because it returns per-place cohort shares rather than listings. It stops short of naming a contrasting sibling such as compare_asking_prices, so the differentiation is by output shape rather than explicit routing.

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 an explicit trigger with realistic user phrasings ('2-bed flats up to 300k in Porto or Valencia', 'and with parking?') and states that rental budgets are unsupported, which rules out a misuse case. It also instructs relay of shares over counts. No sibling alternative is named for cases where the agent actually wants raw listings or price levels.

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