Ask Garçon

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

Annotations already establish the safe read-only, idempotent, closed-world profile, so the bar is lower. The description still adds real behavior: the response is a matching fixmeadrinkapp.com ingredient or glossary page, and health/nutrition questions are out of scope — information not expressed anywhere in the structured fields.

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 paragraph, but it is correctly front-loaded: trigger conditions first, then coverage, then return value, then the scope exclusion. The long parenthetical inventories of covered fields are slightly list-like and could be trimmed, but nothing is redundant with the annotations or schema.

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 and rich annotations exist, so the description only needs to cover scope and routing, which it largely does, including the ingredient-vs-glossary branch. It stops short of explaining behavior on an unknown or ambiguous term (no match found, multiple meanings like a glass vs. a drink style), which is the one operational gap for a lookup tool.

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?

With one parameter at 100% schema description coverage, the schema already carries the meaning, so baseline 3 applies. The description does add marginal value by expanding what counts as a valid term (ingredient names, substitutes, techniques, glassware) and by enumerating the sub-fields returned per term type, but it adds no syntax or format detail beyond the schema.

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

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

A specific verb ("explain") plus an explicit resource set — spirits, liqueurs, mixers, ingredients, and bar terms such as techniques, glassware, tools, and drink styles. That scope cleanly separates it from the recipe- and similarity-oriented siblings an agent would otherwise consider.

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 concrete triggering conditions with three quoted user phrasings ("What is mezcal...", "What can I use instead of Aperol?", "How do I dry shake?"), which is strong positive guidance. It also adds one explicit exclusion (no health or nutrition advice), but never names a sibling as the alternative for adjacent asks like recipe retrieval, leaving that routing 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 only declare that this is a safe, idempotent, closed-world read; the description adds substantial context beyond that: the upstream catalogue, ranking by fewest missing ingredients, a cap of 8 plus up to 2 low/zero-proof options, the meaning of partial:true, and the assumption rules (water and saline assumed, garnishes never block a match). The depends_on behavior tells the agent that ambiguous bottles like 'vermouth' are never silently guessed and should be clarified with the user, which is exactly the kind of trait annotations cannot express.

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-loads the when-to-use trigger and examples before the return contract and caveats, with each sentence carrying a distinct fact. It is on the long side and the optional-filter sentence duplicates the schema, plus the adult/health disclaimer, while defensible, adds a sentence an agent gains little from.

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 tool with four enum/array parameters, a rich output schema and safe read annotations, the description still covers the operational edge cases an agent must handle: result caps, ranking rationale, the partial:true truncation flag, ambiguity clarification, and assumed staples. Nothing needed to call or interpret 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?

Schema coverage is 100%, so ingredients, limit, flavors and strength are already fully documented in the schema, and the description's 'Optional filters: strength (zero_or_low covers mocktails...) and flavour notes' largely restates the enum descriptions. The one added nuance, that ingredient words are taken in the user's own words and ambiguous bottles are never assumed, is useful but leans on output behavior rather than parameter meaning, so the 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 and resource ('Checks their ingredients against the Garçon recipe catalogue') and anchors it with two concrete user phrasings. It also explicitly names the two sibling tools it is not (get_cocktail_recipe, suggest_similar_cocktail), so an agent can route correctly 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-to-use condition (user names ingredients/bottles and asks what they can make), explicit when-not conditions (one named drink, or drinks like one they name) paired with the alternative tool for each, and worked example queries. Nothing about routing is left 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 declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: premium recipes hide the ingredient list, the result flags this and suggests free alternatives, plus adult-only scope and no health/nutrition advice. These are non-obvious response-shape caveats an agent could not derive from 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?

Front-loaded with the use case and examples, then the exclusion, then caveats — a logical order with no filler. It is on the long side and the return-field enumeration partially duplicates the output schema, keeping it just short of a 5.

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 lookup with an output schema, the description covers trigger conditions, the exclusion case, the premium-paywall edge case, and content restrictions. An agent has everything needed to call it correctly and interpret 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?

Schema coverage is 100% and the schema already documents that the single parameter accepts a name, slug, or fixmeadrinkapp.com URL. The description restates the same three accepted forms without adding format or resolution rules, so it adds little beyond the schema — baseline 3.

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 ("Gets that recipe from the Garçon catalogue") and enumerates the returned content (description, glass, ice, garnish, amounts, steps, strength, page). It explicitly distinguishes itself from the sibling find_cocktails_by_ingredients, so an agent can route without opening either 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 concrete when-to-use triggers with example user utterances ("How do I make an Espresso Martini?") and an explicit when-not-to-use rule naming the alternative tool for the ingredient-list case. Nothing is left 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 declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: results carry strength, flavours and a fixmeadrinkapp.com page per drink, plus low/zero-proof alternatives sharing flavour or base spirit, and an audience restriction to legal drinking age. No auth or rate-limit detail, but none is plausible for a public read tool.

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?

Usage guidance is front-loaded before the description of output, which is the right ordering. The single opening sentence is long, packing two quoted example utterances into one clause, but every element still carries routing value and nothing is pure 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 two-parameter read tool with an output schema, the description covers the trigger, the filter parameter, the shape of returned content and the audience constraint. There is no ambiguity an agent would need resolved before calling it.

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

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

Schema description coverage is 100%, so the schema already defines both parameters, including 'low_proof: True to suggest only low and zero-proof drinks'. The description's restatement of low_proof adds no syntax or semantics beyond that, and 'name' is only loosely characterized as the drink the user likes. 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 uses a specific verb+resource: 'Suggests cocktails similar to that one from the Garçon catalogue.' An agent can tell this is a similarity-recommendation tool rather than a recipe lookup or ingredient search. It stops short of explicitly naming the sibling tools it replaces, so it lands at 4 rather than 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?

It states the triggering condition precisely ('when the user names a drink they like and wants something similar, a lighter or lower-alcohol option, or both') and reinforces it with two concrete example utterances. There is no explicit exclusion clause pointing to get_cocktail_recipe or find_cocktails_by_ingredients, which keeps it from a 5.

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