Dunn Estates Aspen: The Galena Penthouse

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety profile is covered. The description adds real value beyond that: the 180-night cap, that data comes from the live calendar, and the privacy limitation that reserved nights appear only as 'reserved' without 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 short sentences, front-loaded with the core capability, followed by return behavior and the next-step pointer. No filler or redundant restatement of the name.

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 two-parameter read tool with an output schema, the description covers the essentials: source of truth, date-range limit, and result shape. Minor gap is that it does not say what happens for ranges beyond 180 nights or how invalid/past dates are handled.

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 schema already explains that start is the arrival/first night and end is the departure morning. The description adds only the 180-night range constraint, which is not itself a parameter-level detail; baseline 3 applies when the schema does the heavy lifting.

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 ('night-by-night availability from the live booking calendar') plus the exact scope ('between two dates, up to 180 nights') and what it returns. This clearly separates it from siblings like get_quote or suggest_dates, which answer different questions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent to get_quote for price and minimum stay, establishing the intended call sequence. It gives clear context but does not name a true alternative for availability itself (e.g., suggest_dates for finding open dates), so no exclusion 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 this as read-only, idempotent, closed-world and non-destructive, so the bar is lower. The description adds meaningful context by disclosing that hotel figures are typical peak-season estimates rather than quotes, which is important for how an agent should present the result.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence plus a short caveat. Every clause carries information: comparators, dimensions, and estimate caveat, with no waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained. The description covers what is compared and the key caveat about estimates. The only minor gap is not stating what happens when the optional alternative is omitted.

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 enum fully documents the optional alternative values. The description names the same alternatives, reinforcing them but adding no syntax or behavior beyond the schema, so 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?

It states a specific verb (compares) and precise scope: The Galena Penthouse against four named Aspen hotels and Airbnb/VRBO on named dimensions. That is clearly distinct from informational siblings like get_amenities or get_property_overview.

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 comparison context implies when to use it, but there is no explicit instruction like 'use when a guest asks how the property stacks up against hotels' or guidance on when to prefer get_amenities. It also doesn't say whether omitting the alternative returns all comparisons.

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 this as a safe, read-only, idempotent, closed-world lookup. The description adds useful scope about what is provided and not available, but does not disclose other behavioral traits such as return format or freshness, though an output schema 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 a single front-loaded sentence with no redundant clauses. The parenthetical examples are dense but each clarifies the amenity scope, including useful negative availability information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity, zero parameters, rich annotations, and existing output schema, the description is complete enough for an agent to call it correctly. It states the resource scope and explicitly covers both available and unavailable amenities.

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 there are no parameter semantics to explain. This matches the baseline of 4 for a parameterless tool.

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 amenities by room and building, with concrete examples of included and excluded features. It implicitly distinguishes this from get_property_overview and get_policies, but does not explicitly name sibling tools or route the agent.

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 explains what the tool returns but gives no explicit guidance on when to use it versus alternatives such as get_property_overview or get_policies. Usage must be inferred from the content 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 already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile needs no restating. The description does add genuine content-scope context beyond annotations — that it returns recurring events with usual dates and live availability for those windows, and travel-time estimates rather than raw distance. It says nothing about data freshness or whether the availability figures are a snapshot versus real-time.

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 dense sentence with no filler, and the most concrete item (address and coordinates) leads. The trailing list of event and transfer clauses runs together without punctuation hierarchy, making it slightly harder to scan than it needs to be.

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 shape need not be explained, and the description does cover the breadth of content. What is missing is the operational context an agent needs: how this differs from sibling overview tools, whether the 'live availability' requires a separate call to check_availability, and what the optional category filter does to the result set.

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 single optional 'category' enum filter is fully documented in the schema. The description never mentions the category filter or that omitting it returns all nearby places, so it adds no parameter meaning beyond what the schema already provides. 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 enumerates the content returned (address/coordinates, walking times, recurring events, live availability, transfer times), so the resource is clear enough. But it is a bare noun phrase with no verb and no scope statement, and it does not distinguish itself from get_property_overview, which plausibly overlaps on address and location detail.

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?

No when-to-use guidance, no exclusions, no mention of alternatives. An agent choosing between this and get_property_overview or check_availability (which the live-availability clause overlaps with) gets no help at all.

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, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds one useful piece of context beyond that: the data is 'as stated in the official property listing', signalling an authoritative, static source rather than a live or negotiated value. It does not address whether policies are property-specific or what happens when a policy is unstated.

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 sentence with no filler; the highest-value topics (check-in/check-out, minimum age, maximum guests) are front-loaded and the list is a legitimate topic index rather than padding. It is dense and comma-heavy, which slightly hurts scanability, but nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With zero parameters, an output schema present, and full annotation coverage, the description only needs to convey scope — which it does thoroughly. The remaining gap is behavioral edge cases (what an agent should do if a requested policy is not listed), which is minor for a static read-only lookup.

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 the baseline is 4 and there is no parameter semantics to explain. The description correctly spends none of its length on input discussion.

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 enumerates the exact policy topics returned (check-in/out times, min age, pets, smoking, quiet hours, parking, taxes, quote and cancellation mechanics), which makes the resource unmistakable and separates it from siblings like get_amenities or get_property_overview. It omits an explicit verb such as 'returns' or 'retrieves', relying on the name to carry the action, but the content scope is specific enough for an agent to select it confidently.

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: an agent can infer it should call this when a guest asks about stay rules, taxes, or cancellation terms. There is no explicit when-to-use statement, no mention of how this differs from get_property_overview or get_quote (both plausible overlaps for taxes/quote questions), and no exclusions.

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

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

Annotations already disclose read-only, idempotent, non-destructive and closed-world behavior. The description adds that the overview includes "honest caveats" and photos, but does not add operational details like auth or rate limits beyond what annotations and the output schema 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 front-loaded with the core content list and followed by the key usage instruction. It is dense but efficient, with every clause contributing to what the tool provides.

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 parameters, rich annotations, and an output schema, the description does all that is needed: it states the scope of facts returned and tells the agent to call it first. Nothing an agent needs in order to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so there are no parameter semantics to document. Per the baseline for parameterless tools, this is adequately specified.

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 exactly what facts the tool returns—size, layout, sleeping capacity, location, highlights, caveats, ratings, permit and photos—and identifies the specific property. This clearly distinguishes it from sibling tools like get_amenities and get_location_and_nearby.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says "Call this first to describe the property," giving clear ordering and context for use. It does not explicitly name when-not-to-use cases or alternatives, but the overview-first role 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 cover the safety profile (readOnly, idempotent, non-destructive, closed world), so the description's added value is the semantic contract: a quote is a live rate snapshot with no hold or reservation, invalid dates and minimum-stay violations are reported back, and a prefilled secure checkout link is produced. That is real context beyond the annotations; only the invalid-date/min-stay reporting format is left unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then the itemization, then the side outputs and the snapshot caveat. Every sentence carries signal; the itemized-taxonomy clause is dense but useful for anticipating the response shape.

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 documented, yet the description still previews the itemization and checkout link. The residual gap is the relationship to check_availability and suggest_dates for prerequisite or fallback flows, which would complete the picture for a multi-tool booking sequence.

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 schema already documents checkin/checkout formats and the 60-night cap and guests bounds, so the description is not required to compensate. It reinforces 'for specific dates' but adds no syntax or constraint detail beyond what the schema provides, so 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+resource (get quote for a property, live all-in) and enumerates the exact composition of the quote: rent, offer, cleaning, property protection, taxes, no platform fee. It also names the side outputs (min-stay rules, invalid dates, prefilled checkout link), which lets an agent distinguish it from check_availability, suggest_dates, and compare_to_alternatives 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?

The scope 'for specific dates from the live booking engine' implies this is the pricing tool once dates are known, and the final sentence clarifies it is a snapshot, not a hold. But no sibling is named and there is no explicit condition such as 'use check_availability first, or suggest_dates if the dates are invalid.' The guidance is implied rather than 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 read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real context beyond them: results are limited to direct-stay reviews (not third-party channels) and ordered newest first, which affects how an agent should present 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?

A single tight sentence with the most decision-relevant facts front-loaded: what is returned, from where, in what order. Nothing wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists and annotations cover the safety profile, so the description needn't explain return values. It supplies the two non-obvious facts (source scope, sort order) but says nothing about defaults or whether the summary is computed over all reviews or only the returned page.

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 limit and minRating both documented in the schema, so baseline 3 applies. The description adds no filtering or default-behavior detail beyond that, and never mentions the minRating capability at all.

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?

Names the resource precisely: a rating summary plus verbatim guest reviews, scoped to direct stays, sorted newest first. This clearly distinguishes it from siblings like get_property_overview or get_policies, though there is no explicit sibling callout.

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 implied by the content (an agent wanting guest sentiment would pick this), but the description never states when to use it instead of get_property_overview or compare_to_alternatives, nor any exclusions. The 'direct stays' scope is the only routing signal.

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, so the description is freed to add operational detail. It does: results respect a typical minimum-stay rule, and only the first few windows carry live all-in totals, which sets expectations about partial pricing 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?

Two sentences: the first defines the output and filters, the second defines the usage context. Front-loaded and free of 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 an output schema present, return shape need not be explained, and the description still flags the key quirk that only the first few windows include totals. Minor residual gap around how many windows are returned per month.

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 month format, guest count, and nights are already documented; the baseline applies. The description maps 'requested length' to nights but adds nothing about the guests cap of 2 or how nights bounds interact with the minimum-stay filter.

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?

Specific verb and resource: lists open stay windows for a given month, filtered by length and typical minimum stay, with live all-in totals for the first few. An agent can distinguish this from get_quote or check_availability by the 'open windows' framing, though no sibling is named explicitly.

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 usage trigger with an example: 'Use it when the guest is flexible ("a long weekend in February")'. This clearly implies the alternative (exact-date availability checking) without naming it or stating an explicit exclusion.

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