RoomLast - Last-Minute Hotels

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds useful scope disclosure — the data is 'undated', meaning it is static property facts rather than time-sensitive availability — which prevents the agent from expecting pricing or availability.

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. The positive scope (what is returned) comes first and the exclusion clause second, which is the correct front-loading for a lookup tool with a nearby offers sibling.

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?

An output schema exists, so return structure need not be described, yet the description still gives a useful content inventory. The main gap is the unexplained 'currency' parameter, which no structured field documents given 0% schema coverage.

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 0%, so the description carries the full parameter burden, and it fails: the 'currency' parameter (with a default of USD) is never explained, and its purpose is only hinted at by saying prices are *not* returned, which is actively confusing. propertyId is gestured at only as 'one identified RoomLast property ID' with no format or sourcing guidance.

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 and resource ('Returns undated facts for one identified RoomLast property ID') and enumerates the exact content returned (address, description, photos, amenities, check-in/checkout times, star rating, guest reviews). It is clearly distinguishable from get_accommodation_offers, which the exclusion clause implicitly names.

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 second sentence explicitly excludes availability, room offers, prices, breakfast, and cancellation terms, which tells the agent when to route elsewhere — notably to the offers sibling. It stops short of naming the alternative tool directly, so it is clear context rather than a full when/when-not/alternative 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 already declare readOnly, idempotent, and openWorld, so the safety profile is covered. The description adds genuinely new behavioral context: results carry masked RoomLast price bands and comparisons, exact private prices and booking must happen on RoomLast — a useful expectation-setting limitation.

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 front-loaded sentences with no filler; the identity scoping, date representation, and return contents come in that order. The enumeration of return fields ('photos, breakfast, refundability...') is slightly long but each item conveys real capability.

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?

An output schema exists so return values need no prose explanation, and the description covers hotel identification, date handling, occupancy, and the masked-price limitation. The only missing piece is the prerequisite that a propertyId typically comes from search_accommodations.

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 85%, so the schema does most of the work, but the description still adds the date-mode semantics (dateIntent 'tonight' vs. the paired checkinDate/checkoutDate) and flags single- versus multi-room occupancy support, which maps to rooms and roomArrangements.

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 one named or identified hotel's live room offers.' The 'one hotel' scoping implicitly separates it from search_accommodations, but it never names the sibling, so the differentiation is inferential rather than explicit.

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 phrasing 'one named or identified hotel's' signals that a propertyId or hotelName must already be known, and it offers two date modes (tonight vs. explicit dates). However, it never says to run search_accommodations first to obtain a propertyId, nor does it exclude any situation or name a sibling tool.

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 read-only, idempotent, non-destructive and open-world traits, so the bar is lower; the description still adds real value by disclosing that prices are masked RoomLast bands and that results carry public-rate comparisons and links, and by stating the exclusion of exact private prices and room options. It omits pagination behavior despite a page parameter.

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 sentences, front-loaded with purpose and scope before the filter and return-value summary. The filter enumeration partially restates the schema and could be trimmed, but 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?

For a 20-parameter search tool with an output schema, the description covers purpose, date semantics, filter scope, and result shape adequately. Minor gaps: no note on pagination limits or how masked price bands should be interpreted downstream.

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 90%, so the baseline is 3; the description adds meaningful semantics by explaining the two date modes (dateIntent 'tonight' versus the checkinDate/checkoutDate pair) and by grouping the filter families (occupancy, price, stars, guest score, property type, amenities, cancellation, sort) into a coherent mental model.

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?

Specific verb ('Finds') + resource (last-minute hotels) + geographic scope (city, neighborhood, airport, landmark) + date scope (tonight or upcoming dates). The closing sentence about what is excluded (room choices, exact private prices) implicitly distinguishes it from get_accommodation_offers and get_accommodation_details.

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?

Clear context for use: last-minute stays for tonight or specified dates, with the supported filter families enumerated. It signals the boundary against offer/detail tools by stating results exclude room choices and private prices, but never names those sibling tools explicitly, so the 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.