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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so safety is covered; the description adds genuinely new behavior: prices are carried over from the originating search with source, fetch time and dates (staleness disclosure), and no fresh pricing call is made. It stops short of describing rate limits or failure behavior when a place name fails to resolve.

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 dense sentences with no filler, front-loaded with purpose before inputs, then outputs, then the pricing caveat. Slight redundancy in restating the return payload ('time and distance to every place, total minutes, ... rank by total minutes') when a full output schema already exists.

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?

Inputs, output contents, price provenance and the boundary against get_hotel_rates are all covered, and return-shape detail is backed by an output schema. Nothing an agent needs in order to call it 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%, so the baseline is 3, but the description adds real semantics beyond the schema: the either/or rule for hotels (hotel_id from search_hotels vs name + lat/lng) and the accepted place identifier forms (lat+lng, station code, IATA, place name). It does not explain the drive/walk traffic allowance beyond what the enum description already says.

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 ('Compares up to 10 hotels by travel time to a set of labelled places') and enumerates the input forms, so an agent can distinguish it from search_hotels and travel_times without opening a schema. The scope (max 10 hotels, max 6 places) is 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?

Gives clear context for use: hotel_ids come from search_hotels, and it explicitly says 'Does not fetch new prices; get_hotel_rates does,' naming the alternative and the condition that selects it. It does not, however, contrast itself with the travel_times sibling, which could plausibly be confused for the same job.

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/openWorld/non-destructive, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the absence of live availability, the requirement of a Confirmed or RAC PNR on the IRCTC portal for booking, and the presence of booking rules and indicative price ranges in the result.

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 sentences, front-loaded with the core capability, then the return contents, then the limitation. No filler; every clause carries information.

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 six optional parameters and an output schema, the description is largely complete and even pre-empts the availability limitation. It is slightly redundant in enumerating return fields that the output schema already defines, but nothing an agent needs to call the tool 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 description coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by framing the two input modes - 'at a station code' versus 'within a radius of a place' - which helps an agent understand that station_code and the place/lat/lng/iata+radius_km path are alternative lookup strategies, not something the schema states.

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 (lists Indian Railways stations with IRCTC retiring rooms) and clarifies the scope with a parenthetical definition of what a retiring room is. It is clearly distinguishable from sibling tools like search_hotels or get_hotel_rates, which cover commercial lodging rather than station-embedded railway accommodation.

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 clear context for use (lookup by station code or by place/radius) and explicitly states a when-not: live availability and exact prices are not available here and require a Confirmed or RAC PNR on the IRCTC portal. It does not name a sibling alternative to use instead, but the exclusion is 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?

Annotations already establish readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: quota, recent success/failure, official vs unofficial endpoints, known limitations, and licence/build date for bundled datasets, which tells the agent what it can learn about reliability before making other calls.

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 sentences, each doing distinct work: scope, per-source contents, and the exclusion. The scope statement is front-loaded and no sentence is redundant.

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 formatting need not be explained. The description nonetheless covers the substantive return fields (enabled state, official/unofficial, quota, limitations, licences) and the key behavioral boundary, leaving nothing an agent needs 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?

The tool takes zero parameters, so per the rubric the baseline is 4. Nothing in the description misrepresents the parameter surface, and no additional parameter meaning is needed.

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 (lists) and resource (every data source this server uses), then enumerates the categories covered. The closing clause 'Does not fetch any hotel data' cleanly separates it from siblings like search_hotels and get_hotel_rates, so an agent can route correctly without opening the 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?

The negative constraint ('Does not fetch any hotel data') implicitly tells the agent this is not a data-retrieval tool but a status/diagnostic one, and the enumerated fields hint at diagnostic use. However, it never states when to call this versus the sibling tools, nor any prerequisite or sequencing guidance.

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, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: aggregation across all booking sources, cheapest-first ordering, currency conversion to INR with original currency retained, tax status, and the explicit 'Does not book' boundary. It says nothing about rate limits, caching, or failure modes for unavailable dates/rooms.

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, zero filler, with the output shape front-loaded before the input guidance and the non-booking boundary last. 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 an output schema present, the description need not explain return values, yet it still outlines them for routing purposes. Combined with full schema coverage, four annotations, and the explicit scope boundary, nothing an agent needs to invoke this 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%, so every parameter including the hotel_id-vs-name+lat/lng alternatives is already documented in the schema. The description restates the identifier options and date scoping but adds no syntax or format detail the schema lacks, making the baseline 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?

States a specific verb and resource (fetch current prices for one hotel across every source) plus the exact output ordering and fields (cheapest first, INR with original currency, tax status, availability, links). The phrase 'one hotel' and the explicit 'Does not book' cleanly separate it from sibling compare_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?

Gives concrete input routing: use a hotel_id from search_hotels or plan_stays, or a name with lat/lng, and states the tool does not book. It stops short of explicitly contrasting with compare_hotels or plan_stays when a multi-hotel comparison is wanted, so the when-not case is only implied.

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 read-only, idempotent, non-destructive, open-world behavior, and the description goes well beyond them: check-in/check-out derivation with early-morning arrivals booking the previous night, the ranking formula (price plus drive time weighted by value_of_time_inr_per_hour), leave-by times with a check-in buffer, IRCTC retiring-room fallback for 3-48 h station stays, and warning conditions. That is unusually rich behavioral disclosure.

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 and free of filler; the opening sentence answers what it does before the mechanics arrive. The middle sentence is dense with stacked clauses (ranking, buffers, retiring rooms, warnings), but that density reflects genuine tool complexity rather than padding.

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 7-parameter, nested-array tool with an output schema, the description covers everything an agent needs: input point formats, temporal edge cases, ranking behavior, fallback options and the non-booking boundary. Return values need not be explained since the output schema exists, yet the description still summarizes them helpfully.

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 already 86%, so the baseline is 3, but the description adds real meaning: it explains that arrival/departure points accept lat+lng, station code, IATA code or place name, that early-morning arrivals shift the booked night, and that value_of_time_inr_per_hour trades transfer time against price. min_stars and max_price_inr remain unelaborated, keeping it from 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 and resource ('Plans where to stay for each stop of a trip in India') and frames the scope at the whole-itinerary level, which separates it from single-point siblings like search_hotels and get_hotel_rates. An agent can tell what this tool produces (ranked stay candidates per stop) without opening the 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?

Usage context is clear: it is the itinerary-level planner, it accepts times 'from any source', and it explicitly closes the loop with 'Does not book', so an agent knows booking is out of scope. It never names an alternative sibling (search_hotels, find_retiring_rooms, compare_hotels) or states when to prefer them, so it stops short of explicit routing.

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, idempotent, openWorld, non-destructive), so the bar is lower. The description adds genuinely useful behavior beyond that: the per-kind search radii (10/60/5 km), straight-line distance semantics, ranked matches, and returned fields.

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 dual-mode purpose followed by detail. Nearly every clause earns its place, though the enumerated radii and field lists make it slightly heavy for a single paragraph.

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 needn't be explained, yet the description still names returned fields. Combined with explicit mode scoping, radii, and exclusions, an agent has everything needed to invoke 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 baseline is 3. The description goes further by explaining the mutually exclusive query-vs-coordinates modes and their distinct semantics, which is meaning beyond the per-field schema text.

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 precise bidirectional verb+resource: name/code to coordinates, or coordinates to nearby transport. It enumerates the exact place kinds (stations, airports, bus stations, landmarks/localities) and explicitly distinguishes itself from siblings with 'Does not 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?

The description clearly scopes the two operating modes ('With query' vs 'With lat/lng'), which is real when-to-use guidance. It lacks explicit routing to named alternatives beyond the negative 'Does not search hotels', so it stops short of full alternative selection guidance.

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/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond them: prices are live and merged across meta-search sources, max_drive_minutes applies OSM routing with a traffic allowance and injects drive_minutes, results are paginated, and 'Does not book.'

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 but front-loaded: purpose first, then accepted inputs, then result shape, then the two sibling pointers. The sentence enumerating returned fields largely restates the output schema, which is mild redundancy, but nothing else 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 an output schema present the description needn't explain returns, and it still covers input forms, pagination, drive-time filtering semantics and the booking boundary. Nothing an agent needs to call this 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%, so the baseline is 3; the description goes further by explaining that the place argument accepts lat+lng, station code, IATA code or a name, and by describing what max_drive_minutes actually does (routing plus traffic allowance, adds drive_minutes). It doesn't clarify include_unpriced or the price-cap interaction beyond 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 and resource ('Finds hotels around a place in India') plus the scope (dates, live merged prices) and explicitly contrasts itself with get_hotel_rates and compare_hotels. An agent can distinguish it from every sibling 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: per-seller prices belong to get_hotel_rates and times to other places to compare_hotels, and it enumerates the four accepted place-input forms. It stops short of stating when-not to use it (e.g. once a hotel id is known), so it is clear context without full exclusions.

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, non-destructive and openWorld, so safety is covered. The description adds real operational context beyond them: the geography restriction (India only), the mode-dependent behaviour (traffic allowance for drive), and a warning when a point is far from any road. That warning behaviour is not derivable from the schema or 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?

Two sentences, front-loaded with the core capability, then the input formats, outputs, and scope exclusions. No filler; 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 an output schema present, the description need not enumerate return fields, yet it still summarises the four returned metrics and the road-proximity warning. Combined with the India-only scope and mode options, an agent has everything needed to call this 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 description coverage is 100%, so each field (mode enum, lat/lng bounds, iata/station_code patterns, place resolution, per-list max items) is fully documented in the schema itself. The description restates the input formats ('lat+lng, a railway station code, an airport IATA code or a place name') but adds no syntax or constraint detail beyond what is already given. 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?

States a specific verb and resource (computes road distance and travel time) plus the scope (matrix from each origin to each destination in India) and mode (by car or on foot). An agent can immediately tell this is an origin-destination routing tool, distinct from the hotel-focused siblings and from resolve_place, which only geocodes single points.

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 description supplies a when-not clause ('Does not cover public transport or flights'), which usefully prevents misuse, but gives no explicit when-to-use trigger and does not name an alternative such as resolve_place for single-point geocoding. Usage is implied (trip planning / matrix comparisons) rather than stated.

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