Portmans Motor Lodge

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

With no annotations, the description carries the full behavioral burden and does so thoroughly: it declares read-only, explains public rate plan selection (default 'BAR - ' title, explicit override), defines the no_public_rate outcome, lists respected constraints (stop_sell, closed_to_arrival, min_stay_arrival, occupancy), and states date rules and that it does not create bookings or accept payment card data. This is exactly the kind of rich context an agent needs.

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 description is a single paragraph but front-loads 'Read-only' and then delivers key information in a logical order. Every sentence carries useful content, though the density and lack of formatting (e.g., bullet points) slightly reduce readability.

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?

Given no annotations, no output schema, and a moderately complex read operation, the description covers all essential aspects: what is returned, rate plan logic, special outcomes (no_public_rate), constraint handling, date rules, and explicit negative guarantees. Nothing an agent needs to call it correctly appears 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 all five parameters are already well-documented in the input schema. The description repeats some date constraints (ISO dates in Pacific/Auckland, check-out after check-in, max 30 nights, no past check-in) but adds no new semantic meaning beyond what the schema provides, making the baseline score of 3 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?

The description states a specific verb and resource: returns room types that fit the stay with nightly and total NZD rates from public rate plans. It is clearly not tautological and an agent can infer it is distinct from get_booking_link and get_property_info, but it does not explicitly differentiate from those siblings.

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 provides clear context for when to use it (checking availability, read-only) and when not to use it (does not create a booking, does not accept payment card data). However, it does not name or contrast with alternative tools such as get_booking_link or get_property_info, so it falls short of a full 5.

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. It usefully discloses the side-effect profile (no booking created, no card data accepted) and that values prefill on the page. It says nothing about scope (no property parameter is passed, so how the target property is determined is unstated) or about failure modes when dates are invalid or exceed the 30-night cap.

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 tightly written sentences, front-loaded with the core action and followed by the two most decision-relevant caveats. The only weak element is the dangling mention of 'currency', which has no corresponding parameter and slightly muddies an otherwise clean statement.

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 6-parameter read-only URL builder with no annotations and no output schema, the description covers the essentials: what is produced, what it does not do, and that inputs prefill. Missing is any note on how the property/booking page is scoped and whether the returned link expires, but the schema fully carries the parameter detail.

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 every parameter in detail (date format, Pacific/Auckland interpretation, occupancy rules, the room_type caveat). The description's 'Dates, guests and currency prefill' adds framing but no syntax or constraints beyond the schema, and it introduces 'currency', which is not a parameter at all. 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: it builds a Channex booking-page URL for the guest to open. The negative clause ('Does not create a booking and does not accept payment card data') sharply separates it from any booking-creation tool. It never names or contrasts with its actual siblings (check_availability, get_property_info), so it stops short of full sibling differentiation.

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 exclusion of booking creation and payment handling implies this is a pre-booking, hand-off step, but there is no explicit statement of when to prefer it over check_availability or get_property_info. A capable agent can infer the ordering (check availability, then produce the link), but it must infer it rather than read it.

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 behavioral burden and does so well: it discloses read-only semantics, the merge/derivation behavior across two sources, that unknown fields surface as TODO, and that no booking or payment card data is involved. It stops short of describing response shape or failure modes.

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 tight sentences, front-loaded with the read-only constraint and leading with the concrete return contents. The 'does not create a booking' clause is slightly redundant given the read-only opener, but it meaningfully pre-empts confusion with get_booking_link.

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 must convey return content, and it enumerates the categories (details, room types, amenities, policies, check-in/out, pool season) plus the TODO edge case. Adequate for a no-arg read tool, though it could say more about how the merge resolves conflicts between Channex and lodge config.

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 there is nothing for the description to clarify; baseline 4 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?

States a specific verb and resource ('Returns Portmans Motor Lodge property details and room types') and even names the data sources (Channex merged with lodge config). It implicitly separates itself from get_booking_link by stating it 'does not create a booking', though it never names a sibling tool 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 is only implied: the read-only framing and the negative statements ('does not create a booking', 'does not accept payment card data') tell the agent what this tool is not for, but there is no explicit when-to-use guidance versus check_availability or get_booking_link.

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