HotelShortlist

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered by structured data. The description adds the topical scope (cost, fee, research process) but says nothing about return format, freshness, or whether any account state is required — useful but not rich. Because the description omits prerequisites, an agent cannot tell whether membership or login is needed to call it.

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?

A single front-loaded sentence with no filler, enumerating exactly the three content areas covered. Nothing needs trimming and nothing important is 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 zero-parameter, read-only info tool with no output schema, the description is nearly sufficient — it names the topics returned so the agent can predict the payload. It stops short of stating the response shape or whether the fee/research details are static, which is a minor gap given the tool's simplicity.

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, which is the baseline-4 case: there is nothing for the description to clarify. The description correctly implies a parameterless global lookup rather than a per-entity query.

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 informational resource — membership cost, fee mechanics, and research methodology — so an agent knows exactly what content this returns. It does not, however, explicitly contrast itself with sibling start_membership_application, so the differentiation is inferable rather than stated.

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: this is the informational lookup that logically precedes start_membership_application, but the description never says when to use it or names an alternative. No exclusions or prerequisites are given.

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 declare readOnlyHint=true and openWorldHint=false, so safety is partly covered, but the description adds no behavioral context beyond loosely naming return content ('with links and WhatsApp contact'). It does not say whether this is a static list, whether results are scoped to the caller, or how the WhatsApp contact should be used.

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?

It is a single short sentence with no padding, which is good, but it is not front-loaded with an action verb or the key fact (that it lists target audiences). The brevity is under-specification rather than efficient concision.

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-param read tool the description must carry the burden of explaining the jargon term 'pitch lane' and what is actually returned; it does not. There is no output schema to fall back on, so the agent cannot infer the response shape.

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; the baseline for a parameterless tool applies. No misleading param claims are made.

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 is a noun phrase ('The offers for travellers, tour operators...') rather than a verb+resource statement of what the tool does, and 'pitch lanes' is never explained. It gestures at content (offers, links, WhatsApp contact) but never tells the agent that this lists segments/audiences with contact details. No sibling (e.g., get_membership_info, search_hotels) is referenced to disambiguate.

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?

There is no when-to-use guidance, no exclusions, and no routing to alternatives such as get_membership_info or request_introduction. The agent must guess the scenario from the name alone.

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 declare openWorldHint=true and readOnlyHint=false, and the description is consistent with that by framing the call as launching external research rather than reading an existing record. It adds behavior the annotations cannot convey: a ~1 minute latency, the requirement to call twice to retrieve the page link (consistent with idempotentHint=true), and a members-only access restriction on rates.

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 clauses, front-loaded with the purpose and the sibling routing before the timing and access caveats. Every sentence carries information, though the member-rates note is only loosely tied to the calling action.

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 usefully covers the two-step retrieval pattern, the ~1 minute latency, and what the resulting page contains (review findings, member-only rates). Only the failure/timeout behavior of the async research is left unspecified.

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% for both parameters, so the schema already documents hotel and city. The description reinforces the pairing ('call again with the same hotel and city') but adds no format or validation meaning beyond what 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 ('Ask HotelShortlist to research a hotel') and immediately distinguishes itself from the sibling search_hotels by scoping to hotels search did not find. An agent can tell this apart from search_hotels without opening either 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?

Explicit routing condition: use it for a hotel that search_hotels did not find, which names the alternative and the condition that selects this tool. It does not spell out a when-not case beyond that implicit opposite, so it falls just short of the top band.

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 a non-destructive write (readOnlyHint=false, destructiveHint=false), so the safety bar is covered. The description adds useful context beyond annotations: the consent precondition and the outcome that 'a person at HotelShortlist replies.' It omits reversibility or follow-up timing details.

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, each earning its place: action, precondition, and outcome. The purpose is front-loaded and there is no 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 an 8-parameter write tool with a fully documented schema, the description covers purpose, the key consent gate, and the expected human follow-up. With no output schema, it could say a bit more about what happens to the submitted details, leaving a minor gap.

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 all eight parameters are fully documented in the schema. The description only reinforces the consent field's importance and adds no new parameter semantics, 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?

The description states a clear action (send a request to HotelShortlist to get in touch) and the resource (a contact/introduction request). It distinguishes itself from request_hotel_page and start_membership_application by its 'get in touch' framing, though it doesn't explicitly contrast with 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 gives an explicit when-to-use precondition: 'Only call this when the person asked for it and explicitly agreed to share these details.' That is a clear gating condition. It stops short of naming alternatives or when-not scenarios.

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 and openWorldHint=false, so safety is covered. The description usefully adds that results are page links whose pages show review findings and an analysis date, but says nothing about result limits, pagination, or behavior on no-match.

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 short sentences, zero filler: the lookup and its inputs come first, the return shape second. 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?

For a one-parameter read-only search with no output schema, the description covers what is searched and what comes back (links plus per-page content), which is nearly enough. Only external details like result caps or pagination are absent.

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% with a single self-documented param ('Hotel name or city'), so the schema carries the semantics. The description restates the same two search axes without adding format, length, or matching behavior, 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 and resource ('Find HotelShortlist research pages') plus the search axis ('by hotel name or city'), so an agent knows exactly what it retrieves. It does not distinguish itself from the sibling request_hotel_page, which is a plausible adjacent step, so it stops short of a 5.

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 phrasing 'by hotel name or city' signals this is the entry-point lookup, and 'Returns page links' hints it precedes fetching a page, but neither the when-to-use nor any exclusion against request_hotel_page is 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=true and openWorldHint=false. The description adds meaningful behavioral context beyond that: the tool only supplies a link and steps and performs no submission, which prevents an agent from misreading it as an application-initiating action. It stops short of describing the return format, but that is minor for a zero-param link tool.

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 short sentences, front-loaded with the resource and immediately followed by the critical scoping caveat. Every sentence earns its place with no 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?

With zero parameters, no output schema, and read-only annotations, the definition is nearly complete: it says what is returned (link and steps) and what does not happen (no submission). Slight gap in not stating whether anything is returned when no open application exists, but that is a minor edge case.

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 are zero parameters and the schema is empty, so per the baseline a 4 applies. The description adds no parameter concerns because none exist.

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 clearly states the tool returns 'the link and steps for applying for membership', a specific resource. It implicitly differentiates from the sibling get_membership_info (informational) by focusing on the application process, but never names an alternative tool directly.

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 person applies themselves; this tool submits nothing' clarifies a key usage boundary — the agent should not treat this as an action tool. However, it gives no explicit guidance on when to call this versus get_membership_info or other membership-related siblings, leaving selection to inference.

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