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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: the data are the map's own daily snapshots (provenance, not third-party market data) and days with fewer than 20 ads return null, which tells the agent to expect gaps in sparse areas. It does not state the time span covered or how many daily points come back.

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?

Two front-loaded sentences with no filler; the core measurement comes first and the null-threshold caveat is appended as a useful qualifier. Minor friction from the awkward 'per day of data' phrasing and the inline Polish gloss '(trend czynszu)', which reads as keyword padding for most agents.

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?

An output schema exists, so return shape need not be described, and the description covers granularity, data provenance, and the sparse-data null rule. The one meaningful gap is the observation window: an agent cannot tell from the definition what period the daily series spans or how far back the trend is computed.

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%, and the schema already explains the 'Warszawa' default, district/neighborhood granularity, and the rooms 1-4 (4 = 4+) convention. The description only echoes the area granularity, adding no new parameter meaning such as name-format or matching behavior for neighborhoods.

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 resource and measurement: median asking rent per day plus the change between first and last day, for a city, district, or neighborhood. That is concrete enough to distinguish it from a point-in-time stats tool, though it never names the closest sibling (rent_stats) that an agent would weigh it against.

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?

Usage is only implied: the word 'trend' and 'change between the first and the last day' suggest this is the tool for time-series direction rather than current levels. There is no explicit when-to-use or when-not-to-use statement, and no routing to rent_stats or compare_neighborhoods for the current-snapshot or comparison cases.

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