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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered; the description adds real behavioral context beyond that: prices are never currency-converted, host data is deliberately reduced to a bare count for privacy, and truncation is reported rather than silently dropped. It does not discuss rate limits or source freshness, but the disclosure is substantial.

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?

Front-loaded with the resource and scope, then filters, then truncation behavior — logical ordering with no filler sentences. It is a dense single paragraph with heavy parentheticals that make it slower to scan than it needs to be.

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?

No output schema exists, and the description compensates by naming the returned fields, pointing to the response's `currency` field, and explaining truncated/total_matching. Combined with the required-parameter contract, an agent has everything needed to call and interpret the result.

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 the schema baseline is 3; the description adds genuine semantics the schema lacks, notably that min_price/max_price filter in the city's local currency and that room_type accepts loose matches. It reinforces the limit/offset paging contract with the truncated/total_matching signal.

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 (listing-level short-term rental rows for one city, sourced from Inside Airbnb) and enumerates the returned fields precisely. An agent can distinguish it from siblings like str_city_summary and list_str_cities without opening a 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?

Explains the required city plus any combination of narrowing filters, and tells the agent to narrow filters or page with limit/offset when results are truncated. It also notes that uncovered cities are refused with the full covered-city list, implicitly routing discovery to list_str_cities, though it never names that sibling explicitly.

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