SplashScout — family water holidays

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful output context ('SplashScout cards', age scores, and features), but it does not disclose anything else about behavior such as matching semantics, errors, or ordering.

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 two short sentences, front-loaded with the core purpose and output format. Every phrase earns its place, and there is no redundant restatement of the tool name or annotations.

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?

This is a low-complexity tool with a single documented parameter, rich safety annotations, sibling context, and an output schema. The description supplies the remaining essential context: the accepted payload size (2–4), the comparison scope, and the output presentation.

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 the ids parameter as 'property ids or names'. The description adds only slight emphasis that either ids or names are accepted, which matches but does not meaningfully extend 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 uses a specific verb-resource pair ('Compare 2–4 family stays side by side') and names a concrete output format ('SplashScout cards', 'age scores and features'). It clearly separates comparison from the sibling retrieval/search tools like get_hotel and search_family_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 implies when to use the tool via 'Compare side by side', which is clear context. However, it does not explicitly state when not to use it or mention alternatives such as get_hotel for a single stay or search_family_hotels for discovery.

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

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

Annotations already declare readOnly, idempotent, and non-destructive, so the description need not re-state safety. It adds useful context about the card contents and that the identifier can be either an id or a name.

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?

One compact sentence front-loads the core purpose and card contents, then closes with the input format. No filler or redundant restatement of the title.

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 an output schema and safety annotations, the description covers what the tool returns and how to target the property. Nothing critical 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% and already documents that 'id' accepts either a property id or name. The description restates this behavior but adds no new format, constraint, or edge-case guidance, matching the baseline for high schema coverage.

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 uses a specific verb ('Show') and names the resource ('detailed SplashScout card for one hotel/campsite'), including concrete content examples (age scores, features, in-person review). The singular 'one' clearly separates it from search_family_hotels and 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?

It clearly implies use when the agent already has an id or name and wants a single property's details. It does not explicitly name alternatives or state, for example, to use search_family_hotels when the id is unknown, so it falls short of a 5.

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, and non-destructive behavior, so the description doesn't need to restate safety. It adds valuable behavioral context by describing the output as interactive cards plus a link to the full guide, and by clarifying this is an editorial ranking rather than exhaustive search results.

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 compact and well-structured: it defines the tool, gives usage guidance, and provides a concrete example. The only minor redundancy is repeating the 'curated/editorial ranking' idea in both the first and second sentences, but overall 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?

For a simple read-only tool with two parameters, full schema coverage, rich annotations, and an existing output schema, the description is complete. An agent can correctly select the tool, build the arguments from the example, and understand what kind of response to expect.

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 schema already provides full descriptions for both parameters, so the baseline is 3. The description adds value by mapping a concrete natural-language example to the parameter values ('destination Turkey, focus splash'), which helps an agent translate user intent into correct arguments.

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 SplashScout's curated, ranked 'Best family hotels/campsites in [destination]' guides, with an overall version or focus-specific versions. It distinguishes itself from search by emphasizing editorial ranking over general search results.

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 explicitly advises 'Prefer this over search for best X in Y questions' and explains why, which gives clear usage context. However, it refers to 'search' generically rather than naming the sibling search_family_hotels, and it doesn't state when the search alternative might be preferred.

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 (readOnlyHint=true, idempotentHint=true, destructiveHint=false), lowering the bar. The description adds genuine behavioral context beyond those hints: it returns 'interactive SplashScout cards plus a text summary' and ranks results by age-group fit. No contradiction with 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?

Three sentences, each earning its place: what it finds, what it returns, and when to use it. The core function is front-loaded before output format and examples. No filler or redundant restatement of the title.

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 all 5 parameters documented in the schema (100% coverage), rich annotations, and an output schema present, the description only needs to carry purpose and trigger conditions — which it does. The only notable gap is explicit differentiation from compare_hotels, but that overlaps with usage guidance and does not hamper correct invocation.

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 adds extra meaning by showing how natural-language prompts map to parameter combinations — 'Tenerife' maps to destination, 'campsites' to type, 'big slides' to features, 'toddler' to ages. It doesn't add syntax details, but the examples genuinely help an agent decide how to fill parameters.

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'), a concrete resource ('hotels & campsites'), and precise scoping ('kid-friendly ... with pools, slides and splash parks, scored for toddlers, kids and teens'). This clearly differentiates it from siblings compare_hotels, get_hotel, and get_travel_guide — it searches and ranks family properties rather than comparing, fetching a single property, or providing general travel guidance.

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 closes with two concrete example prompts ('best family hotel in Tenerife for a toddler', 'campsites in France with big slides') that show exactly which queries should trigger this tool. It stops short of explicitly naming sibling alternatives or stating when not to use it, so it earns a 4 rather than a 5.

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