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 genuinely useful behavioural context beyond that: the data source (realised sales in the cadastral registry), the aggregation (median CZK/m²), the ordering (most expensive first) and the % delta versus the top locality. It does not mention auth, rate limits or handling of localities with insufficient data.

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?

Within each language the content is front-loaded: use-case, return payload, exclusions, scope limit. The bilingual mirroring roughly doubles the length, which is defensible for a Czech-market tool but does mean every sentence appears twice.

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's explanation of what comes back (median CZK/m², sorted descending, % difference vs most expensive locality) fills exactly the gap an agent would otherwise have. Combined with annotations and a fully documented input schema, nothing needed to call this tool 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 the lokality schema already specifies the 2–8 array bound, the district/borough format and the "Praha N" example; the description largely restates these, including the 'streets unsupported' constraint. The jazyk parameter is not addressed at all in the description, and its enum/default is only in the schema. Baseline 3 applies.

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?

States a specific verb and resource (compare 2–8 named Prague localities), the exact metric returned (median CZK/m² from realised land-registry sales), and the sort/delta format. It is clearly distinguishable from every sibling, which is reinforced by naming them in the usage section.

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?

Explicitly gives the when (user wants to compare 2–8 specific localities) and three when-not cases, each routed to the correct alternative tool (ceny_bytu_lokalita for a single locality, top_ctvrti_praha for an unsolicited ranking, odhad_ceny_bytu for an apartment with floor area). It also rules out streets entirely.

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