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

Adds substantial behavioral context beyond the annotations: return payload (amount, currency, accepted terms, private paymentUrl), the no-charge-until-payment guarantee, idempotent resume semantics keyed on same user and stay, and the 409 on paid stays. Annotations cover the safety profile (idempotentHint, destructiveHint=false) and the description layers on the operational details an agent needs at call time.

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 purpose, then packed with distinct behavioral facts, each sentence carrying its own weight. No filler, though the run-on delivery could be tightened slightly.

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 13-param mutation with no output schema, the description proactively discloses the return shape and the key failure/idempotency behavior. Parameter-level detail remains thin in places, but nothing critical for 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 62%, and the description adds only a thin layer ('Provide guests and contact details') over parameters the schema already documents, such as ratePlanCode, roomId, checkIn/checkOut and the guests array. It does not clarify the remaining undocumented params (hotelId, contactName, contactPhone, rooms, adults) beyond what the schema structure implies.

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 ('Create or resume a booking') and ties it to the sibling that produces its inputs ('from get_rates'). The closing 'Does not cancel or modify bookings' explicitly fences it off from update/cancel operations, so an agent can distinguish it from siblings 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?

Establishes the prerequisite chain clearly (rate comes from get_rates) and gives procedural guidance ('Show terms and ask for confirmation before sharing paymentUrl'). It does not name a competing alternative tool for the cancel/modify case, so routing guidance is inferred rather than enumerated.

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, destructiveHint=false and openWorldHint=true, so safety is covered. The description adds genuinely useful context beyond them: the data is 'static catalogue' (i.e. not live/possibly stale) and that prices and availability are absent, plus that includeRooms expands the payload. No auth or error behavior is mentioned, but that is a minor gap given annotation coverage.

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: contents first, the one optional parameter second, the exclusion last. Front-loaded and every clause carries information an agent needs.

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 assumes the burden of describing the return payload and does so field-by-field. It does not cover shape details such as how photos/facilities are returned (list vs. nested, any paging) or behavior for an unknown hotelId, leaving a small completeness gap for a zero-annotation-return 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 description coverage is 0%, so the description must carry the semantics. It does describe includeRooms precisely ('adds catalogue rooms') and ties hotelId to the returned fact set, which is more than the schema alone conveys; only the accepted format/range of hotelId is left to the schema.

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-less but unambiguous retrieval: static catalogue facts for a given hotelId, and enumerates exactly what comes back (address, contact, description, policies, check-in/out, facilities, photos). The clause 'No live prices or availability' separates it from get_rates, and the resource name separates it from search_hotels.

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?

Implied context is clear — call this when you already have a hotelId and need catalogue detail rather than pricing or discovery, and the closing sentence steers away from rate/availability tools. It never names get_rates or search_hotels explicitly, so the routing is inferred rather than stated.

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, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds real value by disclosing the content shape (what to ask, evidence, ranking method) and that it should be consumed before planning, which tells the agent this is static advisory content rather than a live data call.

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 usage trigger is front-loaded in the first sentence and the content summary follows, which is the correct ordering for a read-me-first tool.

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 parameterless, annotation-covered guidance tool with no output schema, the description tells the agent when to call it and what it contains — sufficient to invoke correctly. A small gap remains: it never explicitly says the result is text guidance (vs. structured hotel data), which an agent could infer but must guess.

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 disambiguate; the schema is trivially complete with additionalProperties=false. Baseline 4 applies since no parameter explanation is required.

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 the resource and its advisory role ('planning guide') and enumerates the topics it explains (what to ask, live-rate evidence, how to rank options). It is clear what the tool delivers, though the phrasing 'read before...' describes timing more than the artifact itself, leaving the title to carry the 'this is a guide' framing.

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?

Gives concrete trigger scenarios: flexible dates, budget trips, split stays, multiple destinations, best-hotel comparisons. It implies the guide precedes the sibling tools (search_hotels, get_rates) but never names an alternative or states an explicit exclusion, so routing is inferred 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?

Beyond the readOnly/openWorld annotations, it discloses latency (~15 seconds), an authentication requirement (Fortrip login), rate-limit behavior (429s include retry guidance), a default response-shaping rule (5 cheapest rooms per hotel), and the currency actually charged by the downstream booking call. These are exactly the behavioral facts an agent needs to plan around.

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 scope and return values, then usage sequencing, then operational caveats. Every sentence carries information, though it is denser and longer than strictly necessary for a schema that already documents the parameters.

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, and the description partially compensates by naming what comes back (roomId/ratePlanCode for create_booking, meal and cancellation terms). Combined with full schema coverage, auth, latency and rate-limit disclosure, an agent has enough to call it 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 every parameter is already documented in the schema, including enums and defaults. The description restates counts and currency defaults (1–15 hotelIds, 1–15 nights, CNY default) but adds no format or syntax detail beyond that, so the baseline 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?

Opens with a specific verb+resource and scope: live rooms and rate plans for 1–15 hotel IDs over a 1–15 night stay, with pricing currency and return identifiers named. It is clearly separable from search_hotels, get_hotel, get_planning_guide and create_booking without 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?

Explicitly sequences the workflow: use search_hotels first to find IDs, get_hotel for static policies/photos, get_planning_guide for flexible trips, and this tool to verify availability and quote prices before booking. It also gives a practical usage constraint ('query a few hotels per call').

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 (readOnly, non-destructive, open-world), so the description earns credit for adding semantics: search prices are indicative nightly floors, not bookable rates, and facilities must match catalogue names exactly. It stops short of describing result shape or pagination, so it is strong but not exhaustive.

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, front-loaded, and every sentence carries a distinct payload: search modes, price caveat, facility constraint, error behavior, alternative tool. No filler and the most important routing information (search modes and the get_rates caveat) comes 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 a 14-parameter tool with a nested near object, no output schema, and low schema coverage, the description is helpful on the primary path but silent on filters (price, star, sort) and pagination behavior. With no output schema it could also hint at what a result set contains beyond indicative prices.

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 only 21%, so the description must carry the load and does add meaning for query, cityCode, near, facilities, and currency (CNY default vs USD). However, roughly half the parameters (priceMin/priceMax, starMin/starMax, sortBy, page/pageSize) are unexplained in both schema and description, so the compensation is partial.

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 (Find) and resource (hotels) plus the three ways to scope a search: query (name/brand/city), cityCode, or near coordinates. It implicitly separates itself from get_hotel (single hotel) and get_rates (pricing), so an agent can route 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?

Explicitly routes the agent: use get_rates to quote prices rather than trusting search prices, and use get_planning_guide for complex trips. It also states the failure condition ('Narrow searches refused with 422'), giving a when-not signal rather than leaving the agent to infer it.

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