Plant-Based Nutrition Protocols

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

The readOnlyHint annotation already establishes this as a safe read operation, and the description's 'Generate' is consistent. The description adds value by listing the output components (therapeutic foods, meal structure, etc.), but it does not disclose how parameters like duration_weeks or user_context affect the output.

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 that effectively communicates the action and expected deliverables. It is front-loaded with the verb and resource, contains no redundancy, and every clause adds meaningful 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?

The description provides a good high-level overview of the return contents (therapeutic foods, meal structure, foods to minimize, monitoring markers, citations), but with no output schema and a nested user_context object, it lacks details on output shape and how the optional parameters affect results. More context would be needed for full agent decision-making.

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?

Since schema description coverage is 0%, the description should compensate for unclear parameters. It only references '47 chronic conditions' (matching the condition enum) but does not explain what user_context is for or how duration_weeks influences the protocol. Most parameters remain semantically empty beyond their basic schema types.

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 generates a whole-food plant-based protocol for one of 47 chronic conditions and lists what it returns. It uses a specific verb and resource, and the 'whole-food plant-based' scope distinguishes it from sibling protocol tools, though no alternative is explicitly named.

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 usage context is implied: an agent would infer to use this when creating a plant-based protocol for a condition. However, there is no explicit when-to-use or when-not-to-use guidance, and no reference to alternatives like glp_protocol or query_nutrition_topic.

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, so the read-only nature is covered. The description adds useful context about the source ('200-chunk lifestyle medicine knowledge base') and that answers are 'evidence-based', which is more than the annotations provide. However, it does not disclose limitations such as the scope of the knowledge base or the nature of the returned answer beyond being evidence-based.

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 short sentences that immediately convey the tool's function and source. It is front-loaded with the action ('Ask') and contains no extraneous information, making it highly concise and well-structured.

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 relatively simple, with two parameters and a clear read-only purpose. However, the description does not explain the return format or the role of max_results, and there is no output schema. Given the missing parameter semantics, the description is not fully complete for an agent to use the tool optimally without additional inference.

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 bears full responsibility for explaining parameters. It only references 'query' implicitly through 'Ask a question' but does not explain the structure or expected format of the query, nor does it mention max_results at all. This fails to compensate for the lack of schema descriptions.

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 purpose: 'Ask a nutrition or food-as-medicine question' and specifies the resource ('200-chunk lifestyle medicine knowledge base'). It uses a specific verb and resource, making the intent unambiguous. It does not explicitly differentiate from sibling tools like lifestyle_query, but the domain is clearly nutrition-focused.

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 for nutrition/food-as-medicine questions, but provides no explicit guidance on when to use this tool versus alternatives like lifestyle_query. There are no exclusions or when-not-to-use instructions, so the usage context is implied rather than explicitly delineated.

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