pickyourmatch

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds beyond that: results carry a photo, and the passed context 'stays visible above the results' to preserve search context — a UI/state behavior an agent could not infer from the schema.

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 what the tool returns before the imperative usage guidance. The 'ALWAYS pass...' clause duplicates schema text, but the emphasis is arguably intentional and no sentence is 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?

With 7 optional parameters, no output schema and no required params, the description compensates by describing the returned content (counts, photo) and the calling convention for context params. Nothing critical is missing for correct invocation, though pagination/volume behavior is unaddressed.

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 86%, so the schema already explains adults/children/pets/check_in/check_out and their 'always pass along' requirement. The description mostly restates that instruction; its only added semantic is the rationale that the context remains visible above the results, which is marginal against an already well-documented 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?

States a specific verb and resource ('List all destinations served by pickyourmatch') and even discloses the payload shape (unit counts, dog-friendly counts, a photo). It signals its niche against siblings like search_stays via the 'guest who has not decided where to travel yet' framing, but never names the alternatives 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 clear use condition — 'USE THIS to inspire a guest who has not decided where to travel yet' — and instructs the agent to always pass party and dates already known. There is no explicit when-not rule or named sibling to route to instead, so it stops 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 destructiveHint=false, so safety is covered. The description adds genuinely non-obvious behavior: results link to the property's own calendar with event dates preselected, and the tool is designed to be composed with search_stays. It stops short of return-format or pagination detail.

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

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

Three sentences, front-loaded with the core purpose before the usage triggers, and each sentence carries distinct information (purpose, triggers, composition). Slightly verbose with the quote-heavy examples, but nothing is truly 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?

With an output schema present, the description needn't explain return values, yet it still characterizes the landing page behavior and the cross-tool composition. Nothing an agent needs in order to select and invoke this correctly is missing.

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

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

Schema description coverage is 100%, so all five parameters (query, city, from, to, limit) are already documented with format and semantics. The description adds no syntax or format detail beyond the schema, which is the expected baseline 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 (List) and resource (upcoming events), enumerates the event categories covered, and even describes the shape of each result ('where to stay' page with booking links). An agent can immediately tell this apart from list_destinations, list_packages, and 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?

Explicit 'USE THIS whenever...' trigger conditions, three concrete user-utterance examples, and an explicit orchestration instruction to combine with search_stays. This is close to ideal routing 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety and world scope are covered. The description adds genuine behavioral context beyond that: results render as their own section BELOW unit results and enrich the selection, and each package carries included extras and a direct booking link. It stops short of mentioning auth needs, rate limits, or result cardinality, hence a 4 rather than 5.

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

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

The critical ordering constraint is front-loaded and capitalized, which is the right structure. However, the same ordering rule is restated three times ('AFTER the units', 'never call it first', 'never instead of the unit search'), which is somewhat redundant, and the theme list is repeated between the routing sentence and the resource sentence.

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 9-parameter, no-required, no-output-schema tool, the description supplies the essential missing context: the ordering relationship to search_stays, the thematic trigger conditions, and what a returned package contains. Since there is no output schema, it could say slightly more about the shape/volume of results, but nothing critical for correct invocation is missing.

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

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

Schema description coverage is 89%, so the schema already documents the parameters well (including the 'always pass along' guidance on adults, children, pets, check_in/out). The description reinforces the theme concept by listing romance/wellness/dog/culinary, which maps to the theme enum, but adds no format or filtering detail beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource — 'List themed holiday packages (promotional bundles) across properties' — and enumerates the themes (dog, romance, wellness, culinary) plus what each contains. It explicitly distinguishes itself from the sibling search_stays ('never instead of the unit search'), so an agent can separate it from siblings without opening a schema.

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

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

Gives an explicit when ('when the brief carries a package theme... or the guest asks for deals'), an ordering rule ('call this AFTER search_stays in the same turn'), and hard exclusions ('never call it first, never instead of the unit search'). It also supplies trigger examples ('romantic getaway package', 'dog holiday with meals included'), leaving nothing 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 carry readOnlyHint=true, idempotentHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: each result is a specific unit guaranteed at booking ("what the product states is what the guest is assigned"), and results carry match_score, matched_features and not_confirmed_features. 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?

Front-loaded with purpose and result semantics, which is good, but the long paragraph re-lists every search criterion that the 100%-covered schema already documents in full, so significant text is redundant rather than additive. It is dense but not wasteful to the point of confusion.

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 22 optional parameters and no output schema, the description does well to explain the return shape (one unit per result with floor, view, beds, from-price vs stay-price, booking link) and the naming/availability guarantee. The cursor/coverage pagination semantics live only in the schema, but the description is otherwise 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?

Schema description coverage is 100%, so the baseline is 3. The prose enumerates the same criteria (destination, dates, party, price, features, name, language, limit) that the schema already documents, and adds no syntax, defaults or format detail beyond it; the return-field names (match_score, matched_features) are result metadata rather than parameter semantics.

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 (search) and resource (accommodation: hotel rooms, apartments, holiday homes) at participating properties, with the search-criteria scope enumerated. An agent can distinguish this from list_destinations, list_events and list_packages, which enumerate catalogue entities rather than search bookable units.

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 clear conditional behavior: without dates results carry from-prices, with check_in/check_out they are the units available for those dates with the stay price and booking link; all parameters are optional and query may restate criteria as free text. It does not explicitly route to the sibling tools (events, packages) or state when-not-to-use, so it stops 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.