HomeShared

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

The description goes well beyond the annotations by explaining that the traveler completes sign-in, price review, house rules review, cancellation policy review, and payment in the external checkout flow. It explicitly discloses that no reservation or charge occurs and warns never to pass card details, which is valuable safety context that the annotations do not convey.

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?

Three front-loaded sentences with no waste. The most important constraint, that this is only a checkout link and not a reservation or charge, appears immediately after the core action.

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, but the description names the return value (checkout_url) and explains the downstream flow the traveler will see. Combined with the safety disclosures, an agent has everything needed to call the tool correctly.

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 already documents quote_id as coming from get_quote with a 15-minute lifetime. The description adds meaning by clarifying that the tool checks whether the quote is still available, not merely that it accepts the ID.

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 precise verb and outcome: it checks that a quote_id is still available and returns a checkout_url. It explicitly distinguishes this from an actual booking by saying the tool "reserves nothing and charges nothing by itself," which resolves the ambiguity in the name "book."

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: call it with a quote_id from get_quote when a traveler wants a checkout link. However, the description never names alternatives or states when not to use it, such as what to do if the quote has expired or whether find_cheaper should be consulted first.

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?

Annotations cover read-only and open-world, and the description adds real context beyond them: it reads exactly one public page, performs no Airbnb-side search, and returns an explicit 'no offers' outcome when the home isn't listed elsewhere. The only gap is that it doesn't discuss latency, rate limits, or failure modes when the page can't be read.

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?

Three sentences, front-loaded with the core action and return shape, then scoping constraint, then the no-match outcome. Nothing is repeated from the schema and no sentence is filler.

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 carries the return contract itself and does so fully: per-match all-in total including fees and taxes, savings vs. the Airbnb total, confidence, link, and price-check timestamp. The empty-result case is also covered, so an agent knows how to interpret a success response.

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 all eight parameters including guest breakdowns and airbnb_total are already documented in structured form. The description only restates the URL-plus-dates framing and the savings concept, adding no format or constraint detail the schema doesn't already carry — baseline 3 is correct.

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 — given an Airbnb listing URL, find the same home bookable elsewhere (HomeShared or host site) and return matches with totals, savings, and confidence. The clause 'Reads only that one public Airbnb listing page; it doesn't search Airbnb' separates it cleanly from search_stays, so an agent can route without opening the 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?

The trigger is explicit (you have an Airbnb listing URL plus dates) and there is a clear when-not in 'it doesn't search Airbnb', which points an agent toward the search sibling for discovery. It stops short of naming search_stays/get_quote/book outright, so the alternative routing is implied rather than spelled out.

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?

Annotations already cover the safety profile (readOnlyHint, openWorldHint), and the description adds genuinely non-derivable behavior: the quote is fresh, itemized and all-in, and the returned quote_id expires after 15 minutes. It omits what happens on an unavailable or failed quote and whether price can shift mid-flow, which keeps it off 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?

Two sentences, no filler, with the return value and the critical 15-minute validity window front-loaded in the same line. Every clause carries operational 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?

With no output schema, the description does the work of naming the return payload (itemized all-in price, availability, quote_id) and its TTL, which is enough to call and consume it. Minor gaps remain around failure modes and whether the quote must be re-fetched if booking later than the validity window.

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%, so all seven parameters including the guest-breakdown fields are already documented. The description only adds that the call is scoped to one offer_id and a specific date/guest combination; baseline 3 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 ('Gets a fresh, itemized all-in price and availability') for one offer_id, and names the two sibling tools that produce that offer_id, so the agent can distinguish it from search_stays and find_cheaper 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?

Pins the input provenance (offer_id from find_cheaper or search_stays) and the downstream consumer ('a quote_id that book needs'), which effectively describes the quote-then-book pipeline. It stops short of explicit exclusions, e.g. that a quote is not needed when re-searching or that stale quotes must be re-fetched rather than reused.

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?

Annotations only declare readOnlyHint and openWorldHint; the description adds meaningful behavior beyond them — results are filtered to actual availability, totals include fees and taxes, ordering is cheapest first, and each result carries links and offer_ids. It does not mention latency, empty-result behavior, or whether availability is live, leaving some behavioral gaps.

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?

A single dense sentence that front-loads the action and scope, then the return characteristics, then the usage trigger. No filler clauses or restatement of the title.

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 10-parameter search tool with no output schema and thin annotations, the description supplies what the structured fields do not: result ordering, what the totals include, and the offer_id handoff to get_quote. Nothing essential to correct invocation 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%, so every parameter is already documented, including defaults, ranges, and the all-in USD semantics of max_total. The description adds only the framing that totals are all-in, which the schema already states for max_total — baseline 3.

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 ("Searches vacation rentals") plus the scoping constraint (available for given dates in a place) and the return shape (all-in totals, cheapest first). An agent can distinguish this from get_quote and book without opening the 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?

"Use when the traveler doesn't have a specific listing yet" gives a clear selection condition, and the mention of offer_ids for get_quote implicitly routes the alternative case. It stops short of explicitly naming the when-not case ("if they already have a listing, use get_quote"), so it is strong but not exhaustive.

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