workspace

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

Annotations only declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description goes beyond this by disclosing that the tool requires a sign-in the connection lacks, so it will not return actual data but rather an error with resolution guidance. This is essential behavioral context not present in 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 key constraint (sign-in issue) and the return behavior. The second sentence tells the agent exactly when to invoke and what to expect. No filler words.

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 and no output schema, the description covers everything needed: it explains the tool's intended function, its limitation, and the appropriate action. An agent can confidently call it based on this text alone, even among many siblings.

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, so schema coverage is 100% trivially. The description doesn't need to explain parameters. Per calibration, 0 params gives a baseline of 4. The description adds no parameter info because none exists, so a 4 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: 'returns the reservations arriving on a day,' and immediately clarifies the caveat about sign-in. This distinguishes it from siblings like departures and day_summary by focusing on arrivals. It also explains the actual behavior in this connection (returning an error and fix guidance), which is a clear purpose.

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 gives explicit when-to-use instruction: 'Call it anyway when the user asks for this.' It also explains why it should still be called—because it provides helpful error and fix information. It doesn't mention alternatives, but the instruction is unambiguous and covers the expected scenario.

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 read-only/idempotent/non-destructive annotations, the description discloses a non-obvious behavior: this connection lacks the required sign-in, and calling the tool is still correct because it will return guidance on what is wrong and how to fix it. No contradiction with annotations exists.

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 concise sentences with no filler, and each adds needed information: auth prerequisite, what the tool does, and the directive to call it anyway for the fix message. The most important caveat 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 zero-parameter tool with no output schema and strong annotations, the description covers everything an agent needs: what the tool returns, why sign-in matters, what will happen when called, and how to respond to the user. No material operational detail 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?

The input schema has no parameters, so the baseline is 4; the description mentions conceptual filtering dimensions such as date window, room, and booking number despite there being no formal parameters. There is no schema-level parameter to elaborate, and the description does not need to document formatting.

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 that the tool returns reservations within a date window, by room or booking number, when signed in, so an agent can identify its core function. It does not explicitly reference sibling tools such as reservation_detail or search_stays, so it lacks the contrast that would earn full marks.

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: call it when the user asks for reservations/bookings, and explains why to call it despite the missing sign-in because the tool surfaces a helpful error with how to fix it. It does not discuss when-not-to-use or point to alternatives among the sibling tools, so usage guidance is strong but not exhaustive.

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?

The description adds valuable context beyond the annotations by disclosing the sign-in requirement and that the tool will respond with an error message explaining the issue. This complements the readOnly, idempotent, and openWorld hints, and does not contradict them.

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, with the critical sign-in caveat front-loaded. Every word earns its place, and the description is efficient without missing key 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?

The description is complete for an agent: it explains what the tool does, the failure mode, and the recommended action. No output schema exists, but the description implies the error response is informative, which is sufficient for 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?

There are no parameters, so the description has nothing to add. Schema coverage is 100% by definition, and the description correctly focuses on behavior rather than parameter details, which are irrelevant here.

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 arrivals, departures, and guests in house for a day, which is a specific verb and resource. It does not explicitly contrast with sibling tools like 'arrivals' or 'departures', but the combined nature is evident, so it is clear enough.

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 explicitly instructs to call the tool anyway despite the missing sign-in, and explains why: it will answer with what is wrong and how to fix it. This is direct when-to-use guidance, including an exceptional case, with no ambiguity.

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 read-only, idempotent, non-destructive behavior. The description adds the key behavioral fact annotations cannot: the tool requires a Floreal Workspace sign-in that this connection does not have, so calls will yield an error/guidance response rather than reservations. This disclosure of auth state and expected failure behavior adds real value beyond the structured data.

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 the critical auth limitation front-loaded and the actionable instruction last. Every sentence carries information — requirement, function, and call-it-anyway rationale — with no filler or repetition.

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 tool with no output schema, the description covers purpose, prerequisites, failure behavior, and usage guidance — enough for an agent to invoke it correctly. It could optionally route users to siblings like 'arrivals,' but nothing essential for calling this tool 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?

The input schema has zero properties, so there are no parameter semantics to document; schema description coverage is 100% and there is nothing for the description to add. The baseline of 4 for a parameterless tool applies here.

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: 'returns the reservations departing on a day.' The conditional nature is handled honestly, with the sign-in requirement declared first and the fallback behavior (answering with what is wrong) explained. It doesn't explicitly name siblings, though the name/title pair naturally distinguishes it from the sibling 'arrivals.'

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 gives explicit when-to-use instruction: 'Call it anyway when the user asks for this,' even though the connection lacks the required sign-in, because the tool's error guidance is 'what they need to hear.' This clearly resolves the counterintuitive case, but it stops short of naming alternative tools or explicit when-not conditions.

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?

The description goes far beyond the annotations by disclosing the auth requirement ('Needs a Floreal Workspace sign-in, which this connection does not have'), the success outcome when signed in, and the failure behavior (it explains 'what is wrong and how to fix it'). This is critical operational context that annotations alone do not provide.

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 sentences, each adding distinct value: a critical constraint, the tool's output, and an actionable usage directive. It is front-loaded with the auth caveat, making the most important fact immediately visible. Slightly longer than the absolute minimum, but 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?

Given the tool's simplicity (no params, no output schema) and rich annotations, the description covers everything an agent needs: what the tool returns, the auth limitation, and what happens if called anyway. There is no missing information that would prevent correct invocation or proper handling of the response.

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 has zero parameters and the schema coverage is trivially 100%, so there is nothing for the description to clarify. The baseline for a zero-parameter tool is 4, and the description does not need to add parameter info. It appropriately focuses on behavior instead.

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's function: 'returns occupancy, revenue and KPIs per day, month or year.' This is a specific verb ('returns') and resource ('occupancy, revenue and KPIs'), making the purpose unmistakable. However, it does not explicitly distinguish itself from sibling tools like day_summary, which could partially overlap, 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?

The description gives direct usage guidance: 'Call it anyway when the user asks for this: it answers with what is wrong and how to fix it.' This tells the agent exactly when to invoke the tool despite the known auth failure. It lacks explicit when-not-to-use or alternative routing, 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.

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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful context beyond annotations: the content is published, and answers may appear in Dutch, French, and English, which prepares the agent for multilingual output without contradicting the safety hints.

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 with no filler. The core purpose is front-loaded, and the multilingual detail earns its place without bloating the description.

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 FAQ lookup with one optional parameter, annotations cover safety, the schema covers parameters, and the description covers scope and output language characteristics. Nothing essential 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 the only parameter (domain) is already described as a location slug with omission meaning general questions. The description's phrase 'optionally narrowed to one location' reinforces the schema but does not add meaningful new parameter semantics beyond it.

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 identifies the resource as published questions and answers about Floreal Holidays, with the option to narrow by location. It does not explicitly distinguish itself from siblings like get_menu or search_stays, but the resource type is unambiguous.

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 it—for FAQ content, optionally filtered to a location—but does not state when to prefer an alternative tool or explicitly contrast with siblings. The schema adds the 'omit for the general questions' guidance, which helps parameter usage rather than tool selection.

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, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavior beyond structured data by noting the menus are 'as published by that location' and that availability varies by location, helping agents anticipate missing or location-specific content.

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 concise sentences deliver the core purpose, the scope, the data source, and a key availability caveat. No filler or repetition; 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?

Given the simple tool shape, detailed parameter schema, and robust read-only annotations, the description sufficiently covers what an agent needs to invoke it correctly. It does not describe the return structure, but the absence of an output schema is less critical here since the resource is a straightforward menu retrieval.

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 reinforces that the domain parameter refers to one specific Floreal location and adds the meaningful caveat that not every location publishes menus, which informs expected results for some domain values. This goes slightly beyond the schema without being redundant.

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 identifies the resource as current restaurant and food & beverage menus for one Floreal location, which is specific enough to distinguish it from the sibling tools. It lacks an explicit imperative verb like 'retrieves' or 'lists,' but the noun phrase plus the title makes the purpose unambiguous.

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 provides clear context: this tool returns menus published by a specific location, and it explicitly warns that not every location publishes menus. It does not name alternative tools or state exclusion conditions directly, but the scope and the availability caveat give an agent enough guidance for when to use it.

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 read-only, idempotent, open-world, and non-destructive traits. The description adds valuable behavior beyond that: exact-date-full fallback to alternatives within three days, flexibleDays pricing around the arrival, and the mandatory instruction to share bookingUrl with the guest. 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?

The description is compact, front-loaded with the core purpose, and then adds the few non-obvious behaviors in a logical sequence. Every sentence earns its place; there is no filler or restatement of schema details.

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 explains the key returned information: price, availability, accommodation kind, sleeping capacity, and bookingUrl, plus fallback alternatives. It does not enumerate every possible output field or edge case, but it supplies enough for an agent to invoke the tool and handle the result 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 schema already documents all 10 parameters with descriptions, so the baseline is 3. The description adds cross-tool semantics: packageId originates from list_arrangements, flexibleDays searches surrounding days, and the party concept aggregates adults/children/babies/pets. This meaningfully exceeds what the schema alone provides.

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 precise, specific scope: 'Live all-in price and availability for a stay at one Floreal location, per accommodation type, for the given arrival date, number of nights and party.' It names the output dimensions (kind, sleeping capacity, bookingUrl) and explicitly contrasts with search_stays, so an agent can distinguish it from 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 concrete when-to-use guidance: use search_stays when no location is chosen, pass a packageId from list_arrangements to price a specific package, and use flexibleDays for date-flexible searches. This is explicit routing to alternatives rather than leaving the decision to 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 clearly indicate a read-only, idempotent, non-destructive operation. The description adds the useful contextual fact that gift cards are valid at every location, but it does not disclose the return format, level of detail, or any other behavioral constraints. There is 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?

The description is two concise sentences with no filler. The main purpose is front-loaded, and the added fact about validity at every location is relevant and succinct.

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?

The tool is simple with no parameters, no output schema, and rich annotations covering safety. The description provides the necessary topical scope and a key business rule, making it complete enough for an agent to select and invoke 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?

The tool has zero parameters and the schema coverage is 100%, so there are no parameter semantics to explain. Baseline for zero parameters is 4, and the description does not need to compensate for any missing parameter documentation.

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 provides information about Floreal Holidays gift cards, specifically amounts, languages, and where to buy one. This is a specific resource and topic, and it is readily distinguishable from sibling tools like get_faq, get_menu, or list_locations.

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 this tool should be used when a user asks about gift card amounts, languages, or purchasing locations. However, it does not explicitly state when to use this tool over alternatives or provide exclusion criteria, so usage guidance is implied rather than 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?

Beyond the read-only/idempotent annotations, it discloses date-probing behavior: without a date it probes the next two months and all stay lengths up to a week, including types requiring fixed nights. It also states prices are samples, so the agent won't misrepresent results as firm quotes.

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?

Each of the five sentences earns its place: scope, usage, multi-type caveat, date-probing behavior, and pricing caveat. The most important scoping information is front-loaded, with operational details after.

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?

The definition covers what the tool returns (kinds, sleep counts, indicative prices), how to use it, the meaning of omitting the date, and the limitation that prices are samples. With no output schema, this is sufficient for an agent to call it correctly and route pricing questions to get_stay_price.

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?

Input schema already covers 100% of the parameters, so baseline is 3. The description adds useful extra semantics for the optional arrival parameter (probes lengths up to a week, catches fixed-night types) and confirms domain comes from list_locations, though it mostly restates schema descriptions.

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 opens with a specific verb+resource ('What kinds of accommodation ... offers') and lists concrete examples, making the tool's scope obvious. It also differentiates it from get_stay_price by stating that prices are indicative samples rather than real quotes.

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 says 'Use this for questions about what a location has' with example questions, and warns that prices are samples, directing the agent to 'ask get_stay_price for the guest's own dates'. This gives clear when-to-use/alternative guidance without needing to infer.

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 destructiveHint=false, so the basic safety profile is covered. The description adds useful workflow context: prices are not included and must be requested via get_stay_price using the packageId. It does not describe response format, pagination, or availability behavior, so a 3 is appropriate.

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 with no filler. The first sentence front-loads the resource and key output fields; the second gives a necessary cross-tool instruction. 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 single-parameter, read-only list tool with no output schema, this is complete: it names the input scope, enumerates the returned fields, and explains how to get pricing. An agent has enough information to call it correctly and use its results.

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 fully documents the single domain parameter with an example value ('floreal-blankenberge'), so schema coverage is 100%. The description adds the location-scoped context but no additional parameter semantics beyond what the schema provides.

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 begins with a specific verb and resource: 'bookable packages of one location', and explicitly enumerates the content (stay arrangements, add-on extras, name, description, validity period). This clearly distinguishes it from sibling tools like get_menu, list_accommodation_types, or search_stays.

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 provides clear context for when to use this tool: to obtain the bookable packages for a location. It also directs the agent to get_stay_price for pricing because a package price depends on stay and party, which is an explicit alternative. However, it does not explicitly contrast this with other listing or search siblings.

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 mark the tool as read-only, idempotent, and non-destructive. The description adds valuable context beyond annotations: all locations are in Belgium, the head office has bookable=false and cannot be priced, and the type field has a specific meaning. This is useful behavioral and semantic information.

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 cover the result contents, the domain-argument relationship, the type distinction, and the bookable edge case. Every sentence earns its place and key usage guidance 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 zero-parameter reference-list tool with no output schema, the description is complete: it lists the output fields, explains downstream usage, disambiguates from a sibling tool, and flags the unpricable head office. Nothing needed to call or interpret the tool 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?

The tool has zero parameters, so the baseline is 4. The description still adds value by explaining how fields returned here, especially the slug, feed into other tools as 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 identifies the tool as listing all Floreal Holidays locations in Belgium with a specific set of fields (slug, name, kind, town, region, coordinates). It also distinguishes itself from list_accommodation_types by clarifying that 'type' refers to site kind, not accommodation offerings.

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 tells the agent to use the slug as the `domain` argument for other tools and directs questions about accommodation types to list_accommodation_types. It does not compare itself against every sibling, but the main alternative is clearly named and routed.

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/idempotent annotations, the description discloses a critical behavioral trait: this connection lacks the required Floreal Workspace sign-in, and the tool responds with what is wrong and how to fix it. This tells the agent exactly what kind of response to expect and why the tool is still useful.

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 compact sentences with no filler. The most important fact, the sign-in requirement, is front-loaded, and the call behavior is stated directly.

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 tool with comprehensive annotations and no output schema, the description covers what the tool does when signed in, what it returns, and what happens without the workspace sign-in. An agent has enough context to invoke it correctly and set user expectations.

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 has zero parameters and schema coverage is 100%, so the description has no parameter burden. Baseline 4 applies because with no parameters the description needs to compensate for nothing.

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 says the tool returns one reservation with dates, party size, room, and status, which is a specific verb+resource. It does not explicitly differentiate from sibling search tools like bookings_search or search_stays, but the singular 'one reservation' makes the scope clear enough.

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 states when to call the tool: 'Call it anyway when the user asks for this,' and explains the sign-in limitation that the agent should expect. It doesn't mention when not to use it or name alternative tools, so it stops short of the full 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 mark the tool read-only, idempotent, open-world, and non-destructive, and the description adds substantial behaviors beyond that: results are sorted cheapest first, one option per accommodation type, each result carries a bookingUrl that should always be shared, and when nothing matches the tool returns 'alternatives' within three days. It also clarifies that flexibleDays is a separate widening mechanism on top of the automatic three-day fallback. No contradiction exists 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?

Every sentence earns its place: purpose is front-loaded, usage examples appear immediately after, then filters, result behavior, fallback behavior, and sibling routing. It is dense but not redundant, and the structure follows the natural decision flow 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 must convey what the agent can expect from results, and it does: cheapest-first sorting, one cheapest option per accommodation type, bookingUrl on each result, and alternatives when nothing matches. Combined with annotations covering safety and idempotence, the definition gives an agent everything needed to select and invoke the tool correctly in the intended scenarios.

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 goes well beyond the schema by giving practical meaning to several parameters: region's accepted values, accommodation's enum values plus natural-language equivalents like 'hotel' or 'chalet', maxPrice as the whole-stay all-in euro price, and flexibleDays as a same-call widening mechanism with an automatic three-day fallback. This meaningfully improves an agent's ability to map user requests to 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?

The description opens with a specific verb and resource: 'Find where Floreal Holidays has a stay available, across every location in one call, with the live all-in price per accommodation type.' It clearly distinguishes this tool from get_stay_price by framing it as the location-agnostic search, so an agent immediately knows what it does and how it differs from its 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 explicitly states when to use the tool: 'Use this whenever the guest has not picked a location yet,' and gives concrete guest-language examples. It also names the alternative for the known-location case ('For one known location get_stay_price gives the full picture'), and explains when to narrow with region, accommodation, maxPrice, and when to widen with flexibleDays. This is complete decision 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?

Beyond the annotations, the description reveals a critical behavioral trait: sign-in is required and unavailable on this connection, so the tool will return an error-and-remediation response rather than data. This genuinely helps the agent predict the outcome and decide to call it anyway.

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 each earn their place: one for the auth limitation, one for what the tool returns, and one for how to handle the expected failure. There is no filler or 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-parameter read-only tool with no output schema, the description covers the returned data shape, the auth caveat, and the recommended action when sign-in is missing. Nothing needed for correct invocation is left out.

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 has zero parameters, so the schema already fully covers parameter meaning. The description need not add parameter details, so the baseline of 4 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 states a specific outcome: when signed in, it returns tasks per department and status, which aligns with the 'counts' title. It is clear about the tool's function, though it does not explicitly differentiate it from sibling 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?

The description gives explicit usage guidance: call it anyway when the user asks about tasks, because the tool will respond with what is wrong and how to fix it. It provides clear context but does not name alternative tools or state when not to use it.

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 mark this as read-only, open-world, and idempotent, so no mutation is implied. The description adds crucial operational context beyond the annotations: the connection lacks sign-in, the signed-in behavior, and the failure behavior that returns what is wrong and how to fix it. This fully prepares the agent for the likely error path.

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 sentences with no filler. It front-loads the critical authentication constraint, then states the signed-in behavior and the call-anyway directive in an efficient, readable way.

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 diagnostic read tool with no output schema, the description covers purpose, success behavior, failure behavior, and remediation. An agent has everything needed to decide to invoke it and to interpret the likely response.

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 has zero parameters and 100% schema description coverage, so the schema leaves little to clarify. The description does not need to explain parameters, and the baseline of 4 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 states a clear function: when signed in, it returns who you are and which locations you may look at. It is distinct from sibling tools like list_locations by focusing on the current user's access, though it does not explicitly name or contrast any sibling.

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 clear context about the missing sign-in and explicitly instructs to call the tool anyway when the user asks for this information, because the error-and-fix response is what the user needs. It does not discuss when not to use it or name alternatives, but the guidance is actionable and sufficient.

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