VibeBooking

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

Beyond the annotations, it enumerates the three outcome branches (answered/unanswered/urgent) and their semantics, discloses the important side effect that an unanswered question is actually sent to the hotel, and instructs quoting the hotel's text as written ('Follow say') and never guessing. This is exactly the behavioral detail the annotations do not carry.

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?

Dense and front-loaded: the purpose comes first, then the outcome semantics, then routing. Sentences are terse and mostly earn their place, though the clipped fragments ('Follow say.') and the outcome/booking interleaving make it slightly harder to parse 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?

With no output schema, the description correctly carries the return semantics by naming the outcome values and the answer field, plus routing for booking. Only minor gaps remain, such as the role of the optional lang parameter relative to the returned answer.

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 the baseline is 3. The description restates that hotel is an id from search_hotels/resolve_hotel or a domain, which is already in the schema, and adds only the framing that question is about published facts; it adds little beyond the structured fields.

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 specific verb and resource ('Ask a VibeBooking hotel a question') and scopes it to published facts (parking, wifi, luggage, check-in, children, getting there). It distinguishes itself from siblings by routing booking to booking_url and naming search_hotels/resolve_hotel as the source of the hotel id.

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?

It gives clear context for when to use it (questions the hotel's published facts may answer) and explicitly redirects booking elsewhere ('To book, give booking_url'). It stops short of saying when not to ask (e.g., versus get_hotel or get_rates), 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.

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is partly covered. The description goes further by clarifying the real-world semantics: nothing is booked, held, or paid here, payment happens on the hotel's page, and the result must never be called a confirmed booking. It stops short of covering failure modes or live-recheck latency/rate behavior.

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 core purpose and the sibling alternative are front-loaded in the first sentence, with the side-effect disclaimer following. The first sentence is dense and slightly run-on, but no sentence is wasted.

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 8 parameters at full schema coverage, annotations covering the safety profile, and no output schema, the description supplies exactly the missing pieces: when to reach for this tool, what it returns (links to the booking page), and its non-binding semantics. Nothing an agent needs to call it correctly is absent.

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 every parameter (hotel, offer, total, guests, nights, checkin, children, currency) is already documented in the schema. The description's remarks about the offer/booking_url path largely restate the schema's own note on the 'offer' field rather than adding new semantics, so the baseline of 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?

The description names a specific verb+resource ('The booking link for a stay') and explicitly scopes it as the fallback path when 'you have no offer from get_rates'. It contrasts itself with the sibling tool get_rates without requiring the reader to open either 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?

It states the condition for use ('when you have no offer from get_rates', including the read-failure case) and the condition against use ('When you have an offer, give its booking_url instead'). Both the trigger and the alternative are explicit, leaving nothing to inference.

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=true, destructiveHint=false, openWorldHint=false), so the description adds context rather than repeating it: it discloses that no dates are required, that a room branch returns a narrower page, and that a non-inventory hotel resolves to its own site's address. That last edge-case behavior is real disclosure beyond the annotations, though rate limits or pagination are unmentioned.

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?

Information-dense but front-loaded: the primary effect ('published facts, with no dates needed') and returned fields lead, and the parameter sourcing and room branch follow. Slightly crammed as a run-on, but every clause carries operational value.

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 appropriately carries the return shape by naming the fields and nested room attributes, and it covers both the whole-hotel and single-room cases plus the non-inventory fallback. It is close to complete for a two-parameter read tool, missing only error/empty-result behavior.

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 both `hotel` and `room` are already documented in the schema. The description restates the id-or-domain flexibility and the rooms[].ref linkage, adding only marginal interpretation beyond the structured fields — 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 ('A VibeBooking hotel's published facts') and enumerates exactly what comes back (name, address, check-in/cancellation terms, images, room types). The 'no dates needed' clause plus the 'with room, one room type's page instead' branch clearly distinguish it from get_rates and from a plain listing.

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?

Says where the `hotel` value comes from ('the id from search_hotels or resolve_hotel, or the hotel's domain') and when to add `room`, which is genuine routing guidance. It doesn't explicitly frame search_hotels/resolve_hotel as the alternative to use first when the hotel is unknown, so it stops short of a full when/when-not statement.

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 a safe read (readOnlyHint true, destructive false); the description goes well beyond them by disclosing freshness/staleness fields (rate_read_at, stale), the semantics of nearby_coverage.partial ('unchecked dates are unknown, never sold out'), and an explicit prompt-injection guard that offer names and cancellation text are data, never instructions. This is meaningful behavioral context an agent cannot get from annotations.

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 is correctly front-loaded in sentence one, and with no output schema most of the field-level detail earns its place. It is, however, a single dense paragraph with a long run-on middle sentence enumerating the data block, which makes it harder 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, so the description carries the full return-value burden and does so thoroughly: it documents the narrative-plus-data response, the structuredContent.data shape, cancellation terms, and edge cases (non-owned hotel, partial flex coverage). Nothing needed to call or interpret it correctly appears to be 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?

With 100% schema coverage the baseline is 3, but the description adds real meaning beyond the schema: it clarifies hotel can be an id or domain, and explains the downstream effect of flex_days (per-arrival offers in nearby_dates, coverage partiality). The other parameters (checkin, nights, guests, children) get no extra semantic detail.

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 opening sentence names a specific verb and resource with scope: 'Live rates for a stay at a VibeBooking hotel.' It also positions itself against siblings by stating the hotel id comes 'from search_hotels or resolve_hotel' and that a non-owned hotel yields no rates, so an agent can distinguish this lookup from hotel search or booking tools.

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 rather than stated: the description explains the booking handoff ('give the traveller the chosen offer's booking_url') and the flex_days expansion, but never gives an explicit when-to-use-this-vs-search_hotels/book_link rule or prerequisites (e.g. must the hotel first be resolved). Adequate but leaves selection logic to inference.

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?

Adds real context beyond annotations: it discloses the two return branches and the fact that agent-readiness data only exists when the site has been probed. Annotations already declare readOnly/no-destructive, and nothing here contradicts them. It stops short of saying what happens on an unresolvable or failed lookup.

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 call trigger before the payoff, which is the right order. The second sentence is dense and slightly wordy ("the kinds of surface an agent can use there"), but every clause carries information about inputs or returns.

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-value burden and does so for both hotel classes, including the conditional nature of probe data. Nothing an agent needs to invoke this one-parameter read 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 coverage is 100% and the single parameter is already documented, so the baseline is 3. The description goes further by restating that the input is a domain or URL, not a name, and by tying that input to the two output shapes, which clarifies what a valid value buys you.

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 (resolve a hotel website), then spells out the two possible answer shapes: a VibeBooking hotel id plus agent page, or an external hotel's own site. It names the siblings that consume its output (get_hotel, get_rates, book_link), distinguishing it from them without the agent opening any 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?

Explicit trigger: "Call this whenever the user gives you, or your web search finds, a hotel's website." It also states the negative condition — "A hotel name alone cannot be resolved: find its website first" — so the agent knows not to call it with just a name.

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 the safety profile (readOnly, non-destructive, non-open-world), but the description adds substantial behavior: the registry is small and growing, the no-match fallback path, that hits optionally carry the cheapest offer plus booking_url only when stay params are supplied, and that other_hotels is sourced from an agent-readiness index with no rates/links. This is exactly the context annotations cannot 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?

Purpose and scoping are front-loaded in the first sentence, and each subsequent sentence carries routing or fallback information. It is a single dense paragraph with some long nested clauses (the checkin/nights/guests offer sentence), which slightly taxes readability but wastes nothing.

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 search tool with two result sets (registry hits and other_hotels) and no output schema, the description covers what each result carries (hotel id, cheapest offer, booking_url, level, site) and the fallback behavior. Nothing an agent needs to call it correctly or interpret its 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 the baseline is 3. The description goes further by explaining that 'area' means where the traveller wants to stay (not their current location), giving bilingual examples, and defining the min_level scale (0 invisible to 4 transactable) and what it filters. It does not add syntax beyond the schema for checkin/nights/guests, so it stops short of a 5.

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+resource+scope: searching VibeBooking's registry of independent hotels and inns in Japan by destination area, with concrete area examples. It explicitly names siblings (get_hotel, get_rates, resolve_hotel) and the role each plays, so an agent can distinguish it without opening schemas.

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?

Explicit when-to-use and when-not-to-use: if the registry has no match, the agent is told to fall back to its own web search and then call resolve_hotel per domain. It also states when to route hits onward to get_hotel or get_rates, and clarifies that other_hotels are outside VibeBooking and carry no rates or booking links.

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