Cups to Grams

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

The annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no restating. The description instead adds real behavioural context: the density data is measured (not guessed), the corpus is 271 ingredients, and the response reports which cup definition was applied and cites the source. That last point is valuable output-behaviour disclosure in the absence of an output 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?

The purpose and the ingredient-optional rule are front-loaded, and every other sentence does work. The single long unit enumeration is dense but earns its place because the unit parameters are free-form strings; still, it reads as a wall of nouns rather than a structured list.

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 read-only five-parameter converter with a fully documented schema and no output schema, this covers the decision points an agent faces: which units exist, how cup ambiguity is resolved, when an ingredient is mandatory, and what the result reports about its own provenance. Only ingredient-name resolution failures are unaddressed, a minor gap against an otherwise complete picture.

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?

Coverage is 100%, so the baseline is 3, but the description goes further by enumerating the accepted unit vocabulary (including the six cup definitions and the spoon/fl-oz/butter-stick families) for free-form string parameters whose schema only supplies partial examples. It also reinforces that explicit units like metric_cup override cup_system, which is the subtlest interaction in the call.

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 opening sentence states a specific verb (converts) and a precise resource (a kitchen amount between volume and weight for a named ingredient), plus the data basis (USDA portion weights with FDC ids, King Arthur chart). This is unmistakably distinct from the sibling tools convert_oven_temperature, search_ingredients, and scale_recipe.

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 establishes the condition that selects the ingredient parameter — "Volume to volume and weight to weight need no ingredient" — which is exactly the decision an agent needs to make. What it lacks is any routing to siblings, e.g. pointing at search_ingredients when the exact ingredient name is unknown.

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 safety (readOnly, idempotent, non-destructive, closed-world), and the description goes further by disclosing the 20 C fan offset rationale, the gas-mark table bounds, and that results are rounded to the nearest gas mark with an exactness flag. That rounding/exactness behaviour is real substance not present in 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?

Two sentences, front-loaded with the core conversion and followed by the return-value note; nothing is padded. The first sentence is dense with parentheticals, which costs a little readability but every clause carries 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?

With only three simple parameters, no output schema, and annotations covering safety, the description supplies everything an agent needs: input scales, gas-mark bounds, fan handling, and the shape of the returned gas mark plus exactness flag.

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 enums for both fan and from_scale, so the schema carries the baseline. The description still adds meaning the schema lacks: the allowable gas-mark span (1/4 to 10) and the magnitude/source of the fan adjustment (20 C, manufacturer guidance), which tells an agent what the enum values actually do.

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 ('Converts') plus the exact resource ('an oven setting') and the three scales involved, including the gas-mark range 1/4 to 10. It also names the optional fan adjustment, so an agent can tell immediately this is a temperature-unit tool and not the ingredient converter among the 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?

The description implies when it applies (converting an oven setting across F/C/gas, with or without fan adjustment) but never states explicit conditions, prerequisites, or when to prefer convert_ingredient instead. Usage is inferable from the title and description rather than spelled out.

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, and the description adds genuinely new context: mixed-number and fraction-character parsing, the measured density table used for gram conversion, and that unmatched lines are reported back. It does not characterize failure modes beyond unmatched lines.

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, front-loaded with the core action and supported by illustrative examples. Every sentence carries information, though the density is on the higher side.

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 carries the burden of describing return values, and it only partially does so—mentioning reported unmatched lines but not the shape of the successful scaled output (e.g., strings vs. structured quantity/unit/gram triples). For a tool this data-shaping, that gap matters.

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 schema already documents every parameter thoroughly, making 3 the baseline. The description does add one relationship not encoded in the schema—that factor is an alternative to original_servings/target_servings—but does not elaborate further.

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 names a specific verb and resource (scaling ingredient lines) and gives concrete input examples, so an agent immediately knows what the tool consumes. It does not explicitly contrast itself with the sibling convert_ingredient, which handles single-ingredient conversion, leaving that boundary to inference.

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 two supported modes clearly: scale by a factor, or scale from original to target servings, plus the optional to_metric_weights mode. It stops short of naming when to prefer this over convert_ingredient or search_ingredients.

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. The description adds useful context beyond annotations: search is fuzzy, results include canonical names and density values with provenance from USDA FDC or King Arthur Baking. It does not discuss ranking or pagination beyond the limit parameter.

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 compact sentences, front-loaded with the core action and scope, followed by return values and usage guidance. There is no 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 simple read-only lookup with two fully documented parameters and no output schema, the description covers what the tool searches, what it returns, and how it fits before conversion. An agent has enough information 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?

Schema description coverage is 100%, so both query and limit are already documented with examples and bounds. The description adds no additional parameter guidance, which matches the baseline 3 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 ('Fuzzy search over the ingredient table'), lists the covered categories, and names the concrete return fields (canonical names, grams per cup/tablespoon, source). This clearly distinguishes it from conversion tools like convert_ingredient.

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 to use it 'to pick the exact ingredient before converting,' which positions it relative to convert_ingredient. It stops short of naming when not to use it or pointing to an alternative search method, but the usage context is clear.

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