Hotelumo Hotel Operations

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile needs no restating. The description adds the 'or not-found' outcome, which is genuine behavioral information beyond the annotations, but says nothing about permissions, error conditions, or lookup constraints such as whether the hotel must be active.

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 short sentences, front-loaded with the trigger and scoping constraint. The middle sentence re-lists return fields that an existing output schema already covers, so it is mildly redundant, but nothing is padded or ambiguous.

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 one fully documented required parameter, rich annotations and an output schema present, the description covers everything an agent needs: when to call it, what it returns conceptually, the not-found case, and what it is not for. No material gaps remain.

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?

There is a single parameter and schema description coverage is 100%, with the schema itself documenting the 24-hex-character id format and pattern. The description adds no extra meaning about the identifier, so the baseline 3 applies since the schema does all the work.

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 ('get one hotel's setup') and enumerates the concrete attributes returned (check-in/check-out times, currency, country, timezone). It also explicitly rules out neighboring concerns ('Not for room availability or prices'), so an agent can separate it from get_hotel_availability and list_daily_rates 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?

Gives a clear trigger ('Use this when someone asks about one hotel's setup') plus an explicit exclusion for availability and prices. It does not name the specific sibling tool to use instead (e.g., get_hotel_availability), so routing is implied by category rather than stated, but the when/when-not framing is present.

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, so the safety profile is covered. The description still adds real behavioral context beyond them: results are filtered to rate plans that have availability on every night for the party, prices are in minor currency units, and searches are bounded to 1-30 nights and check-in within 365 days.

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 usage trigger, then what is returned, then constraints and the exclusion. No filler or redundancy; each sentence carries distinct 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?

With an output schema already present, the description need not enumerate return fields. It supplies the scope, the availability filter semantics, currency-unit convention, and date-range limits, which is everything needed to call the tool 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 every parameter (dates, headcounts, hotelId format) is already documented in the schema. The description's date-window constraints largely restate what the schema says, and it adds no new syntax or party-composition detail. 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?

The description names a specific resource and scope: it returns room types and rate plans with a free room every night for the party, plus inventory counts and prices. The filtering semantics ('free room every night') are more precise than the title alone. It does not name any sibling (e.g. list_daily_rates, list_rate_plans) as the adjacent alternative, so it falls 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?

It gives a concrete trigger ('when someone asks if rooms are free for certain dates or what a stay would cost') and a negative boundary ('Not for making a booking'). It does not, however, steer the agent toward or away from any actual sibling tool that overlaps on rates or room lists.

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, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds real operational context beyond that: a default 7-day window, a 31-day maximum, and a counting cap of 500. It does not explain response shape, but the output schema makes that unnecessary.

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 triggering intent, followed by the return contents and limits, then the exclusion. No filler and nothing buried.

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 read-only aggregate tool with full schema coverage and an output schema, the description supplies everything an agent needs: what is counted, the default and maximum window, the 500 cap, and what the tool is not for. No meaningful gap remains.

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%: dateFrom/dateTo defaults, the inclusive YYYY-MM-DD format and the 31-day limit are all documented in the schema already. The description's window and cap statements largely restate that, so baseline 3 is appropriate with no added syntax or format detail 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?

The description states a specific verb and resource: it returns daily counts of arrivals, departures and in-house stays, plus reservation totals by status. That is concrete enough to distinguish it from lookup-style siblings like get_hotel or list_rooms 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?

It gives an explicit trigger ("Use this when someone asks how busy the hotel is, or how many arrivals, departures or in-house stays fall on each day") and an explicit exclusion ("Not for looking up a guest or reservation"). It does not name a specific sibling tool as the alternative for a caller who wanted an occupied-rooms view, so it falls just short of the 5 bar.

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 closed-world, so the safety profile is covered. The description still adds value by disclosing the not-found outcome, which annotations do not convey.

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 short sentences with zero waste; the trigger condition is front-loaded, followed by return shape and then exclusions. Every clause earns its place.

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, return values need not be spelled out, yet the description still summarizes them. For a one-parameter read tool with full annotation coverage, the only minor gap is not naming the sibling to use for prices or dates.

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% and the single roomTypeId parameter is fully documented in the schema, including its 24-hex-character pattern. The description adds no format or lookup semantics 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?

States a specific verb (get) and resource (room type) and names exactly what it returns: name, hotel, maximum guests. The exclusion of prices and free dates cleanly separates it from rate/availability 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?

Gives a clear triggering condition ("when someone asks about one room type") and explicit exclusions ("Not for its prices or free dates"), which routes the agent away from list_daily_rates and get_hotel_availability. It stops short of naming the alternative tool to use instead, so it is strong but not maximal.

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, and closed-world behavior. The description adds useful operational context beyond annotations: the 90-day range limit and the default behavior that 'days without a row use the plan's base price.' It does not cover auth or rate limits, but it meaningfully extends the behavioral picture.

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 three tightly written sentences. It is front-loaded with the usage trigger, follows with the return behavior and fallback semantics, and closes with the exclusion. Every sentence earns its place.

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. Annotations cover the safety profile, and the description supplies the usage trigger, scope, fallback behavior, and explicit exclusion. Nothing an agent needs in order 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 description coverage is 100%, so the schema already documents all four parameters with patterns and descriptions. The description reinforces that the tool operates on one rate plan and specific nights, but adds no syntax or format detail beyond the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

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: it 'Returns the stored per-day price and restrictions of one rate plan over up to 90 days.' It also distinguishes the tool from siblings by specifying that it is 'Not for whether rooms are free,' which contrasts with the availability-focused tools.

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 gives an explicit when-to-use trigger ('when someone asks what a rate costs on specific nights, or about minimum stays, stop-sell or closed-to-arrival dates') and an explicit when-not ('Not for whether rooms are free'). The exclusion effectively routes the agent away from availability tools, even though the alternative tool is not named by exact name.

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, idempotentHint, non-destructive and closed-world, so safety is covered. The description adds real behavioral context beyond that: only *active* extras are returned, prices are in minor currency units, and results are paginated at 20 per page by default.

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, zero filler: the first front-loads the use case and the key returned fields, the second states the exclusion. Nothing is redundant or buried.

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 full param coverage, an output schema handling return values, and annotations covering the safety profile, the description supplies everything else an agent needs: domain scope, active-only filtering, price units, pagination, and the exclusion boundary.

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%, with limit, offset and hotelId all self-documented including defaults and the offset+limit paging recipe. The description only echoes the 20-per-page default already present in the schema, so it adds little beyond the baseline.

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+resource ('list extras a hotel sells') and enumerates the domain (breakfast, parking, spa, transfers, fees) so an agent can distinguish it from siblings like list_rate_plans or list_daily_rates. It also closes the boundary with 'Not for what a guest bought or was charged.'

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 trigger explicitly ('Use this when someone asks what extras a hotel sells... and what they cost') and pairs it with a negative condition ('Not for what a guest bought or was charged'), which is the main risk of misuse for an extras-listing 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 establish readOnly/idempotent/safe semantics, but the description adds real value beyond them: the returned field set (id, name, currency, language, timezone), the 20-per-page default, and what is deliberately excluded (no addresses or guest data). It does not describe error or auth behavior, so it falls short of a 5.

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 short sentences ordered by importance — trigger, return shape, exclusion — with no filler and 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?

For a zero-required-param list tool with an output schema and full annotation coverage, the description supplies everything an agent needs: when to call it, what comes back, and what it is not for.

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?

Both parameters are fully documented in the schema (limit 1-100 default 20, offset 0-10000 with offset+limit paging guidance), so the description's mention of "20 per page by default" only restates it. With 100% schema coverage, baseline 3 is 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 (list) and resource (hotels/properties the user manages) and explicitly carves out scope with "Not for room availability," separating it from get_hotel_availability and list_room_types. An agent can identify this tool's job 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?

Gives a concrete trigger ("when someone asks which hotels... or a hotel's id is needed") and one exclusion ("Not for room availability"). It stops short of naming the alternative sibling tool to use instead, so routing still needs a small 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?

Annotations already cover the read-only/idempotent/non-destructive profile, but the description adds genuinely new context: the returned field set (title, room type, base price, meal plan, per-room/per-person, default flag) and the pagination default of 20 per page. It does not mention auth requirements or total-count behavior, so not a full 5.

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: trigger, returned payload, then exclusion. Front-loaded and 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?

With an output schema present and full schema coverage, the description need only establish purpose, scope, and the date-specific exclusion, all of which it does. Nothing essential 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 coverage is 100%, so all four parameters including limit/offset syntax are already documented in the schema. The description only restates the 20-per-page default, adding no meaning beyond the schema; 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 concrete verb+resource (list rate plans) plus what is returned (base prices), and explicitly carves out the boundary against date-specific pricing. An agent can distinguish it from list_daily_rates without reading 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?

Gives a clear triggering condition ('when someone asks what rate plans a hotel sells... and their base prices') and an exclusion ('Not for prices on specific dates'). It stops short of naming the alternative tool to use instead, leaving that inference to the agent.

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, so the safety profile is covered. The description adds genuinely useful context beyond that: the default page size of 20 and the privacy constraint that no guest or occupant data is returned. It stops short of describing pagination limits or ordering, which keeps it out of the top range.

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 packed sentences: trigger condition first, return contents second, exclusion last. No filler, and the most decision-relevant information is front-loaded.

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, yet the description still summarizes the salient return shape, and it covers the filter parameters implicitly via the schema. For a read-only list tool with full annotation coverage, nothing an agent needs to select or invoke it 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 limit/offset/hotelId/roomTypeId semantics are already fully documented in the schema. The description adds the pagination default but does not mention the hotel or room-type filters, so it neither compensates for nor extends the schema meaningfully. 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 (list) and resource (rooms) with the exact status dimension it exposes — clean/dirty/inspected, out of order/service. It also names what the result contains (name/number, room type, hotel, statuses), which an agent can use to differentiate it from siblings like get_hotel_availability.

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 explicit trigger conditions ('when someone asks which rooms are clean, dirty or inspected') and an explicit exclusion ('Not for which rooms are free on given dates'), which routes the agent to the availability tool for the adjacent use case.

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, idempotentHint, destructiveHint, and openWorldHint, so the safety profile is covered. The description adds genuinely new behavioral context beyond the annotations: the sort order (by name) and the default pagination size (20 per page).

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 use condition, then the return/sort/paging behavior, then the exclusion. No filler and every sentence carries a distinct piece of 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?

With a full output schema, complete parameter descriptions, and annotations covering the safety profile, the description only needs to cover scope, ordering, paging default, and boundaries — all of which it does. 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 description coverage is 100%, so limit, offset, and hotelId are already fully documented including defaults, ranges, and the offset+limit paging hint. The description only restates the 20-per-page default, adding no syntax or semantics beyond the schema; baseline 3 is 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 ('List room types') and frames it in the user-language scenario ('what kinds of rooms a hotel offers or how many guests each room type sleeps'), which lets an agent distinguish it from siblings like get_room_type (singular) and list_rooms.

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 gives an explicit when-to-use trigger and an explicit when-not ('Not for whether a room type is free on given dates'), which routes the agent away from this tool toward the availability sibling. The only gap is not naming that alternative by exact name, but the exclusion condition is unambiguous.

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, closed-world. The description adds real context beyond that: it enumerates what the card contains (reservation status counts for next 7 days, room/room-type/room-status/housekeeping counts), notes these come from bounded samples, and explicitly excludes guest, stay and payment data — useful privacy/scope 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?

Three sentences that are tightly ordered: usage trigger, then return contents, then exclusion. No filler or redundancy, and the most decision-relevant information (when to use) is front-loaded.

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 single-parameter read tool with rich annotations and an existing output schema, the description supplies everything else an agent needs: what it returns, the bounded-sample caveat, and what data is deliberately absent. Nothing material 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?

Single parameter with 100% schema description coverage (pattern and format already documented in the schema). The description adds no syntax or constraint detail for hotelId, so the schema does all the work — baseline 3.

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 ('Show') plus the resource ('hotel operations overview' / dashboard) and constrains scope to one hotel. It also names the adjacent-but-different case ('Not for a single reservation'), letting an agent separate it from get_hotel and get_hotel_schedule_summary.

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 a clear triggering condition ('when someone wants a quick overview or dashboard of one hotel's operations') and one explicit exclusion ('Not for a single reservation'). It stops short of naming which sibling to use instead for detail or schedule, so it is strong but not fully routing.

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