Airbnb MCP

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

No annotations exist, so the description carries the full burden and does so: it discloses live scraping from airbnb.pl, latency (~1 s direct, ~10 s via unblocker fallback), that dated calls issue two requests, that host contact details are deliberately omitted, that Polish wording is returned, and what `available: false` means with the note explaining why. This is exactly the behavioral context an agent needs before calling.

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?

Purpose and pricing behavior are correctly front-loaded, but the single-sentence 'Result: { ... }' dump of every nested field is a dense run-on wall of text that is hard to scan. The content is largely justified (there is no output schema), yet the delivery is unstructured enough to slow an agent down.

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 9-parameter, no-annotation, no-output-schema tool, the description covers purpose, cost/latency, request count, output shape, availability semantics, and known limitations (language, no price without dates, no host contacts). Nothing material is missing for correct invocation.

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 baseline is 3, but the description adds meaning the schema does not: it ties checkin/checkout and the guest counts to concrete output effects (total price incl. fees, price_per_night, price_before_discount, availability). It does not explain the interplay of adults/children/infants or the no_cache caching semantics beyond what the schema already says.

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?

Opens with a specific verb+resource ('Full details of one Airbnb listing') and immediately enumerates the facets returned, which cleanly separates it from the sibling airbnb_search (which finds listings rather than detailing one). An agent can pick between the two 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?

States the key conditional: 'With checkin/checkout it also returns the price... Without dates there is no price (Airbnb prices only dated stays)', which tells the agent when the tool is and isn't useful for pricing. The relationship to airbnb_search is only implied here (the ID sourcing is spelled out in the schema, not the description), so the when-to-use-vs-alternative guidance isn't fully explicit.

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

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

With no annotations, the description carries the full burden and does so: discloses the data source (scraped live from airbnb.pl), latency profile (~1 s direct fetch, ~10 s via unblocker fallback), the 270-result / 15-page cap, the 5-minute cache implied by no_cache, currency/price-basis semantics, 28+ night monthly quoting, approximate blurred coordinates, and Polish-language field values.

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 purpose and key caveats, and most sentences earn their place, but the long enumeration of the full result object and per-listing field list is largely redundant given an output schema exists. It is dense and information-rich but would benefit from trimming the return-shape prose.

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 14-parameter scraping tool with no annotations, it covers pricing basis, pagination limits, caching, latency, language quirks, failure semantics and sibling handoff. Nothing an agent needs to call it correctly or interpret results 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 coverage is 100%, so baseline is 3, but the description adds genuine meaning beyond the schema: `price` is the all-in total for the stay for the given guests, `price_per_night` = price ÷ nights, `price_before_discount` is the struck-through total, `page` caps at 270 results across 15 pages. It doesn't restate per-parameter constraints (guests caps, date formats) that the schema already covers, which is appropriate.

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 (search places to stay on Airbnb) plus property types and geographic scope, and explicitly separates itself from airbnb_listing ('Pass a listing's `id` to airbnb_listing for amenities, house rules and the host'). An agent can route between the two siblings 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?

Gives explicit when-tos and when-nots: pass checkin+checkout to get a comparable quoted total, omit both to get Airbnb's suggested-stay prices which are 'not comparable and not a quote'; use `page` 2–15 for more results; use airbnb_listing for amenities. It even explains that an empty match is a successful result with guidance, not an error.

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