Cocktail Glass

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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds substantial behavioral context: case- and diacritic-insensitive substring matching, the 'gin' vs 'sloe gin'/'ginger beer' example, result limit of 60, fields returned (name, URL, family, glassware), and catalogue ordering. It does not contradict annotations, and the extra detail is exactly what an agent needs beyond 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?

The description is a tight three-sentence paragraph: purpose first, then matching details and example, then result shape and alternative. Every sentence adds unique value; there is no filler or repetition of schema/annotation content. It is front-loaded and highly scannable.

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 (one parameter, no output schema) and strong annotations, the description leaves nothing critical unaddressed. It explains input constraints, matching behavior, output limit and structure, ordering, and the key alternative for multi-ingredient use cases. The description is self-sufficient for an agent to invoke 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 covers the 'ingredient' parameter fully (type, examples, minLength, description) but the description enriches it further by explaining the matching semantics (substring, case/diacritic-insensitive), warning about comma-separated lists being treated literally, and clarifying that the parameter is single-valued. This goes well beyond the structured schema, making the parameter behavior unambiguous.

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 every cocktail in the catalogue that uses one specific ingredient.' It clearly distinguishes itself from siblings by stating it accepts exactly one ingredient and explicitly contrasts with find_makeable_cocktails for multi-ingredient queries. The substring matching detail and result scope further clarify its niche.

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 says 'Takes one ingredient only' and directs users to find_makeable_cocktails for multi-ingredient queries, even noting that tool handles near-misses. It also advises using a more specific term when substring matching may cause false positives, giving concrete situational guidance. This exceeds the minimum for when-to-use/alternative clarity.

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 discloses key behavioral details: case- and diacritic-insensitive matching, up to 60 results, ordering by year then cocktail name, and the possibility of a cocktail appearing multiple times. These go beyond the annotations (readOnlyHint, openWorldHint) and provide valuable context about results and edge cases.

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 well-structured and front-loaded, starting with the core purpose. Every sentence serves a purpose—usage, matching rule, output format, limits, and sibling differentiation—without redundancy. It is appropriately concise for the complexity.

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 (one parameter, no output schema), the description covers all necessary aspects: what it does, how to use it, behavior details, and return format. It is self-sufficient and leaves no critical gaps for an AI agent to invoke it 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 description significantly enriches the 'movie' parameter by clarifying that it is a substring matched against both title and scene description, allowing characters or actors as valid inputs (e.g., 'Bond', 'Hemingway'). This meaning is absent from the schema, which only states 'A film or TV show title, full or partial.'

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: 'Find every cocktail that appears in a given film or TV show.' It uses a specific verb and resource, and explicitly distinguishes itself from siblings by noting 'Use this only for on-screen appearances; for a drink by name use search_cocktails, and to browse the whole catalogue use list_cocktails.'

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?

Provides explicit guidance on when to use the tool: 'Use this only for on-screen appearances; for a drink by name use search_cocktails, and to browse the whole catalogue use list_cocktails.' It also explains matching behavior and gives examples, making it clear when a character or actor name can be used.

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 and closed-world annotations, the description reveals key behavioral details: matching is word-based not substring, garnishes are optional, water is assumed but soda/tonic are not, list caps (60/25), ordering by simplicity then name, and omission of drinks needing 2+ missing ingredients. This is exceptionally transparent and adds substantial value over the 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 long but every sentence carries meaningful information: purpose, matching rules, list contents, limits, ordering, and usage guidance. It is front-loaded with the core purpose and structured logically, with no wasted words 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?

Despite having only one simple parameter and no output schema, the description fully explains return values (makeable and almostMakeable lists, missing ingredient names, caps, ordering) and edge cases. It is self-contained and leaves no significant gaps for an agent to guess about.

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 describes the 'ingredients' parameter with a clear description and examples, so the baseline is 3. The tool description adds nuance about acceptable ingredient terms and matching behavior, plus optional garnishes, which helps the agent construct valid inputs. This extra context justifies a 4.

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: given ingredients, find fully makeable cocktails and near-makeable ones. It uses a specific verb ('find') and resource ('makeable cocktails'), and explicitly distinguishes from the sibling tool for single-ingredient searches, making its purpose unmistakable.

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 tells the agent when to use this tool: 'Use this for multi-ingredient "what can I make?" questions; for a single ingredient use find_cocktails_by_ingredient.' This provides clear usage context and names the alternative, exactly what good usage guidelines require.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds valuable behavioral details: case- and diacritic-insensitive matching, exact-match-first then substring fallback, and the return contract (one cocktail object or an { error } object). This goes beyond the annotations without contradicting 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?

The description is three sentences with no redundancy: the first states the primary function and return contents, the second explains matching behavior and errors, and the third gives usage guidance. All sentences earn their 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 single-parameter read-only tool, the description is fully self-contained. It specifies the exact return fields, the error format, and the alternative tool to use, making it complete despite lacking an output schema.

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 covers the 'name' parameter with descriptions, examples, and guidance. The description adds extra nuance about case/diacritic insensitivity and the substring fallback, enhancing understanding. Since schema coverage is 100%, the baseline is 3, but the added semantics justify a 4.

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 retrieves the full recipe for one cocktail by name and enumerates the recipe content (ingredients, steps, garnish, glassware, family, URL, media appearances). It explicitly differentiates from siblings by emphasizing 'by name' and directing ambiguous cases to search_cocktails.

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 explicit when-to-use guidance: 'Use this when you have a specific drink name' and when not to use it, recommending search_cocktails for ambiguous names or lists. It also clarifies the matching fallback, giving complete usage context.

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

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

Annotations declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds extra behavioral context: results are presented 'in catalogue order', include a specific summary format, and the tool 'returns every matching cocktail' with no cap. It also notes that omitting family lists the entire 500-drink catalogue, which isn't obvious from annotations alone.

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 yet information-dense. The first sentence defines the action and output, the second explains when to use it versus siblings, and the third gives alternative tools. Every sentence earns its place, and it is front-loaded with the core behavior.

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 list tool with one optional parameter and no output schema, the description covers all essential aspects: the result set (whole catalogue or family), summary fields, ordering, the 500-drink scope, and explicit usage guidance. It leaves no significant gaps.

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 covers the 'family' parameter exhaustively: it lists all valid family values, notes exact case- and diacritic-insensitive matching, and states that unknown families return an empty list. The description merely says 'optionally restricted to one drink family' without adding meaning beyond the schema, so the baseline of 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 clearly states the tool lists the entire catalogue of cocktails as summaries with specific fields (name, URL, family, glassware), distinguishing it from sibling search tools. The verb 'List the whole catalogue' precisely describes the action and resource.

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 contrasts with search_cocktails and find_cocktails_by_ingredient (cap results, need query), and states to use this when there is nothing specific to search for. It also points to get_cocktail_recipe for a named drink and find_cocktails_by_ingredient for ingredient discovery, providing clear when-to-use and alternatives.

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 readOnlyHint annotation, the description discloses that draws are independent ('repeated calls give different drinks'), the family matching is exact yet case- and diacritic-insensitive, and that an unmatched family silently falls back to the full catalogue. These behaviors are not encoded in annotations and materially influence expectations.

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 compact paragraph where each sentence covers a distinct aspect: action, randomness, filtering, and usage versus alternatives. No filler words or redundant restatements.

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 (one optional parameter, read-only), and the description covers the full behavior: selection method, return structure, filter semantics, fallback, and use cases. The absence of an output schema is mitigated by explicitly listing the returned recipe fields.

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 describes the 'family' parameter and lists valid values plus the fallback. The description adds the case- and diacritic-insensitivity rule and clarifies that omitting the parameter yields an unrestricted pick. This is valuable but not a large increment because the schema already handles most of the 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 opens with 'Suggest one cocktail picked uniformly at random from the catalogue' and details the return payload (ingredients, measures, steps, garnish, glassware, URL, appearances), making the action and scope explicit. It also distinguishes this tool from siblings by naming alternative tools for specific use cases.

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 states 'Use this only when the user wants a suggestion or inspiration with no specific drink in mind,' and gives concrete alternatives: 'For a named cocktail use get_cocktail_recipe; for "anything with gin" use find_cocktails_by_ingredient; for "what can I make from what I have" use find_makeable_cocktails.' This is textbook when/when-not 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?

The annotations already mark it read-only, but the description adds substantial behavioral context beyond that: substring matching, case/diacritic insensitivity, ranking order (exact > prefix > suffix > substring), result cap of 25, and the list of summary fields returned. This gives the agent a detailed model of what the tool does without any 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 three sentences, each earning its place: core behavior with examples, return format with ranking, and usage guidance with alternatives. It is front-loaded with the most important information and contains zero filler.

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

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

For a search tool with no output schema, the description fully covers the return value (up to 25 summary results with name, page URL, family, glassware), matching behavior, ranking, and a clear link to the next step (get_cocktail_recipe). Combined with annotations and schema, 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?

Although the schema covers the query parameter well (name or part, examples, minLength), the description adds meaningful semantics: it clarifies that query is a single drink name, and describes the matching behavior (substring, case/diacritic-insensitive) and the ranking effect. This goes beyond the schema's description, enriching the parameter meaning significantly.

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 searches the cocktail catalogue by name, with specific matching behavior (substring, case/diacritic-insensitive) and returns summary results with a defined ranking. It also distinguishes this from sibling tools by explicitly naming get_cocktail_recipe and find_cocktails_by_ingredient as alternatives, so purpose and differentiation are both clear.

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 this tool: when the user names a drink (even fuzzily) to confirm existence or disambiguate similar names. It also provides exclusions and alternatives: use get_cocktail_recipe once a single name is known, and use find_cocktails_by_ingredient for ingredient-based discovery. This is exemplary usage guidance.

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