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

Annotations already establish a safe, idempotent read, so the description's added values are meaningful: every fact carries a source and check date, prices and opening hours are deliberately excluded, and partially-covered cities return an explicit 'not covered yet' answer rather than failing silently. It does not describe response shape or how many sections come back by default, but the annotations lower that bar.

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 content inventory comes first, then the sourcing and exclusion caveats, so the tool's payload is front-loaded. The lead sentence is a long run-on list, but nearly every clause (source/check date, no prices, partial coverage) adds decision-relevant information.

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 a read-only lookup with full schema coverage and no output schema, the description supplies what the structured fields cannot: what topics exist in practice, what is intentionally absent, provenance of the facts, and the partial-coverage failure mode. Only the default section behavior and language handling are left entirely to the schema, which is acceptable.

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 three parameters are documented, so the baseline is 3. The description's topic enumeration loosely maps to the `topics` enum and its coverage caveat hints at `city_id` behavior, but it adds no format details (e.g. id form, language effect) 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 enumerates the exact content returned (best months, crowd seasons, airport/station/port transfers with typical minutes, city passes, free sights, booking requirements, closing days, dress codes), which makes the resource unmistakable. It does not name or distinguish itself from near siblings like get_city_guide or get_attraction, leaving the boundary to be inferred.

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 implied through the topic list and the scope exclusion 'No prices or opening hours', which steers an agent elsewhere for those facts, but no alternative tool is named and there is no explicit when-to-use/when-not-to-use statement. The coverage caveat ('Researched for some cities only') is a data property, not selection guidance.

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