Hôtel Bonne Nuit - Labuan Bajo

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

Beyond the annotations, it discloses the crucial behaviors: the reservation is unpaid, the room is blocked for only 15 minutes, the booking is auto-cancelled if payment does not arrive, and the cancellation terms change from free to non-refundable five days before arrival. It also notes that pricing is computed by the hotel rather than by the caller, which prevents an agent from sending a price.

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?

Four tight sentences: what is created, what is returned, the timeout consequence, the cancellation terms, then the input prerequisites. Nothing is redundant and the highest-value facts (unpaid, 15-minute block, payment_url) come first.

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 an 11-parameter mutation tool with no output schema, the description covers the outcome (payment_url), the transient state (blocked room), the failure mode (auto-cancellation) and the pricing source. An agent has everything needed to call it correctly and to explain the consequences to a user.

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 82%, so the schema already documents most inputs; the description only restates the required set (room_id, dates, name, email, policy acceptance). It adds no meaning for adults, children, phone or notes, which are the parameters most likely to be misused.

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 opens with a specific verb and resource ("Crée une réservation NON PAYÉE") and immediately states the return value ("renvoie un lien de paiement Midtrans (payment_url)"). The creation/payment-link purpose is unmistakably distinct from the read-oriented siblings check_availability, get_hotel_info and list_room_types.

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 prerequisites for a valid call: a room_id "d'une chambre disponible", the dates and client identity, plus explicit acceptance of the cancellation policy. Availability checking via check_availability is strongly implied but never named as the required alternative, so the routing guidance stops just short of 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?

Beyond the readOnlyHint/openWorldHint annotations, the description discloses meaningful behavior: the 30-night cap, that prices are the TOTAL for the stay and exclude breakfast, and that each available room carries a book_url to the official engine. It does not mention rate limits or behavior when no rooms are available.

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 dense sentences, front-loaded with the core purpose and scoping constraint, followed by pricing and return-value information. No filler, though the parenthetical currency and duration notes are slightly compressed.

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 usefully explains the return payload (room_id, book_url, total price per available room). It leaves the occupancy parameters' semantics and no-availability behavior unexplained, a modest gap for a 4-parameter read tool.

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 50%: checkin/checkout are documented in the schema, while adults and children have no descriptions anywhere. The description contributes only the 30-night range constraint on the date parameters and adds nothing about occupancy limits (max 3 adults, 1 child), so the other half of the parameters remains undocumented.

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+resource combination: availability and prices per room type for a stay, with currency (IDR) and duration limit. It is clearly distinguishable from book_room and list_room_types by implication, though no sibling is named explicitly.

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 context is implied by the max 30-night constraint ('séjour max 30 nuits') and by the pricing note, but there is no explicit guidance on when to call this versus list_room_types or before book_room. The agent must infer that this is the pre-booking availability check.

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 openWorldHint=false, so the safety profile is covered. The description adds real value by enumerating the categories of data returned (address, times, amenities, payment, cancellation, contact), which is important because there is no output schema. It does not state whether the data is static or live, but for a read-only info tool that is a minor gap.

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 front-loaded sentence with a scannable content list and no filler. The geographic qualifier (Labuan Bajo, Komodo, Indonésie) earns its place by disambiguating the property.

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 and no parameters, the description carries the burden of telling the agent what comes back, and it does so via the field enumeration. Adding a note on whether these are fixed property facts versus reservation-specific details would make it fully complete.

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?

The tool takes zero parameters, so the baseline of 4 applies. The description correctly implies no input is needed and frames the call as a fixed lookup for one specific property.

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 the exact resource (general information about Hôtel Bonne Nuit in Labuan Bajo) and enumerates what it covers: address, check-in/out times, amenities, payment methods, cancellation policy, contact. This clearly separates it from siblings like book_room and check_availability, which are transactional. It stops short of a leading verb, but the resource and scope are unambiguous.

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 only implied: an agent can infer this is the tool for static hotel-detail questions while the siblings handle booking and availability. There is no explicit 'use this when...' statement or mention of the alternatives by name. Adequate but leaves routing 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?

The annotations already declare readOnlyHint=true and openWorldHint=false, so safety and scope are covered structurally. The description adds that the set is a fixed catalog of exactly four types with fixed attributes, which is modest but real context; it says nothing about whether data is static across calls or how results are ordered.

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 sentence with the verb and the enumerated scope front-loaded, and the returned attributes in a trailing parenthetical. No filler, no redundancy.

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 burden of conveying what comes back, and it does so by naming the four room types and the attributes per type (beds, exterior, capacity). For a zero-parameter read tool, nothing essential 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?

The tool takes zero parameters, so the baseline is 4 and there is nothing for the description to compensate for. The mention of lits, extérieur and capacité usefully signals what each entry carries, though this is return-side rather than parameter information.

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 ("Liste") and resource ("types de chambres") and then enumerates the exact four values returned (Double bâtiment 1, Triple, Double bâtiment 2, Twin). This makes clear it is a static reference catalog, distinguishing it from check_availability and book_room without needing the 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?

Usage is only implied: an agent can infer this is the tool for retrieving the fixed room-type catalog before booking or checking availability, but the description never states when to use it or that no arguments are required. No alternatives are named or excluded.

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