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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered and the bar is lower. The description still adds real behavioural value the annotations lack: the data provenance (realised sales in the Czech land registry, median CZK/m²) and the side use for discovering valid district names. It does not describe pagination or truncation when fewer districts exist, so not a 5.

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?

Content is front-loaded and split into clearly delimited CZ/EN and use/do-not-use segments, so it scans quickly. It is longer than strictly minimal because the entire guidance is duplicated in both languages, but that duplication is justified by the bilingual audience.

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?

With no output schema, the description correctly covers the return ordering and data source, and annotations cover safety. Minor gaps remain for a list tool: the shape of each returned district record and what happens when the district count exceeds the ranked set are not stated, but nothing essential to calling it correctly 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 description coverage is 100% and all four parameters carry rich bilingual descriptions including enum meanings, default and range, so the schema does the heavy lifting and a 3 baseline applies. The description reinforces the district/borough scope and the median CZK/m² sort, but adds no syntax or format detail beyond the schema.

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+scope: it returns a ranking of Prague (or one borough's) districts sorted by median CZK/m² from realised cadastral sales. It also explicitly distinguishes itself from the comparison and single-locality siblings, so an agent can choose it without opening any 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?

There is an explicit "use when" clause (ranking questions: most/least expensive districts, affordability) and an explicit "do not use when" clause that routes to the correct sibling by name (srovnani_ctvrti for named localities, ceny_bytu_lokalita for one locality, odhad_ceny_bytu for a specific apartment). Nothing is left to inference.

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