Drug-Food Interactions

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

Annotations already declare readOnlyHint=true, so the safety profile is known. The description adds value by specifying the three dimensions covered (food-drug, nutrient depletion, timing-critical dosing), which are specific behaviors beyond the annotation. It doesn't describe output format or edge cases, but the added specificity exceeds baseline.

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 single, well-structured sentence that immediately states the tool's purpose. It contains no redundant words and front-loads the core functionality 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?

The tool has two parameters and no output schema. The description covers the main purpose and mentions the required parameter implicitly, but omits the optional 'foods_or_supplements' parameter and provides no hint about return values or result format. Given the moderate complexity and existing annotations, the description is adequate but leaves clear 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?

Schema description coverage is 0%, so the description must compensate. It mentions 'medications' implicitly but never explains the 'foods_or_supplements' parameter, nor does it specify expected string formats (e.g., generic names, brand names). The description adds minimal meaning for the required parameter and none for the optional one.

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 'Check' with a clear resource ('list of medications') and enumerates three precise check types (food-drug interactions, nutrient depletions, timing-critical dosing). This clearly differentiates it from sibling tools like drug_safety or lifestyle_query, which cover adjacent but distinct domains.

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 a clear usage context: when the user wants to assess interactions between medications and food/nutrients/timing. It does not explicitly mention alternatives or when not to use the tool, but the context is strong enough that an agent can infer when to invoke it. Lack of explicit exclusions 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.

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

The readOnlyHint annotation already indicates a safe read operation, lowering the burden on the description. The description adds the constraint of 'single medication' and specifies the food-drug domain, but it does not disclose return format or potential limitations. This matches the pattern from the TDQS 4.3 calibration example.

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 single sentence with no unnecessary words. It is front-loaded with the action and resource, making it immediately understandable.

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 has only one parameter and no output schema. The description gives the core function but does not clarify what the 'food-drug safety profile' contains, how to handle unknown medications, or how it differs from check_interactions. It is adequate for a simple tool but has clear 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?

Schema description coverage is 0%, so the description must compensate. It only implies that the 'medication' parameter should be a single medication name, but gives no format, accepted identifiers (generic vs brand), or examples. This adds minimal value over the parameter name itself.

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 action (Return), a precise resource (food-drug safety profile), and a scope (single medication). This clearly distinguishes it from sibling tools like check_interactions, which likely handle multiple drugs, and get_protocol, which covers protocols.

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 phrase 'for a single medication' gives clear context for when to use this tool, implying it is not for multi-drug or general interaction queries. However, it does not explicitly mention exclusions or name alternative tools, so it falls 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.