KinToolkit: Medicine Dosage Calculator Label References for Children and Infants

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

With all annotations set to false, the description carries the full behavioral burden and delivers: unlisted medicines are unsupported, do not drop or substitute, ambiguous matches return clarification guidance, reference-only products are separately marked with sources, and arguments/results are excluded from telemetry. This goes well beyond the structured metadata.

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 dense but compact, with mapping examples and constraints front-loaded before output details. Every sentence contributes meaningful guidance; there is no filler or repetition of schema content.

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?

Since an output schema exists, return values do not need to be restated. The description covers input conventions, unsupported cases, output categories, ambiguity handling, and privacy, giving an agent everything needed to decide when to call it and how to construct valid calls.

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?

Only one of three parameters has schema documentation, but the description compensates by mapping public product names to enum values: Children's Motrin means brand motrin + audience children, Zyrtec means brand zyrtec, generic cetirizine means ingredient cetirizine, and Walmart means brand equate. This is essential semantic information not present in 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?

The description states a specific verb ('Resolve') and resource ('ordinary public product names') and gives concrete mapping examples that make the function unambiguous. The mention of 'matching calculator bottles and separately marked reference-only' formulations also distinguishes it from sibling tools like get_label_directions and list_calculator_bottles.

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 gives explicit guidance: omit filters only when unspecified, do not substitute unlisted products, and reject free-text/patient inputs. It does not explicitly name alternative sibling tools for routing, but the boundaries are mostly inferable from the output categories it describes.

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?

With all annotation hints false or absent, the description carries the behavioral burden. It discloses the ask_doctor fallback, the exclusion of child-suitability assessment, and that operational telemetry records no arguments or results—useful behavioral context beyond 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?

Three tightly scoped sentences cover the action, prerequisites, return values, limitations, and telemetry. The core purpose is front-loaded, and every sentence adds new information without fluff.

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 three-enum lookup with a provided output schema, the description is nearly complete: it explains input provenance, exact-match requirements, output contents, and safety caveats. The only minor omission is explicit no-match/error behavior, which is likely handled by the output schema and is not critical here.

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 0%, so the description must compensate. It clarifies product_id/concentration as requiring an exact bottle/concentration match and connects label_band to age/weight restrictions only indirectly. The enum values are largely self-explanatory, but label_band is not explicitly mapped.

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 object ('Look up one public label row') and identifies where the identifiers come from, distinguishing it from list_calculator_bottles. It also lists exact return contents, so an agent knows precisely what this tool does.

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 states a clear prerequisite: use identifiers from list_calculator_bottles and require an exact bottle/concentration match. It also flags a non-goal ('Does not determine suitability for a child'), which helps prevent misuse, though it does not explicitly name alternative tools or exhaustive when-not-to-use cases.

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?

All four annotations are false, so the description carries the burden of behavioral disclosure. It adds two useful behavioral facts beyond the annotations: 'No patient inputs' (privacy scope) and 'Minimal operational telemetry records no tool arguments or results' (logging behavior). The verb 'list' strongly implies a read-only, non-mutating operation, so no side-effect ambiguity exists. It does not explicitly say 'read-only', but the description adds meaningful context beyond 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?

The description is two sentences with zero filler. The core purpose is front-loaded, followed by two concise behavioral constraints. Every sentence earns its place, and no information is repeated or extraneous.

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 zero-parameter list tool with an output schema present, the description covers what is needed: it lists five US liquid medicine bottles, confirms no patient inputs, and notes telemetry limitations. Since the output schema exists, the description doesn't need to detail return structure. Nothing an agent needs to 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?

The tool has zero parameters and the schema is empty with 100% coverage, so the baseline is 4. The description adds no parameter-specific detail, which is appropriate; it only reinforces that no patient inputs are expected, aligning with the empty 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?

The description states the exact action ('List'), the resource ('the five supported US liquid medicine bottles'), and the specific contents (exact concentrations and public label-band identifiers). This clearly distinguishes it from the sibling tool get_label_directions, which handles directions rather than enumeration.

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 usage through its title and first sentence, and the phrase 'No patient inputs' hints that this is a general reference not tied to a specific patient. However, it does not explicitly mention the sibling tool get_label_directions or provide any when-not-to-use or alternative-routing guidance, leaving usage context only implicit.

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