Generate an evidence-based whole-food plant-based protocol for one of 47 chronic conditions. Returns therapeutic foods, daily meal structure, foods to minimize, monitoring markers, and clinical citations.
| Name | Required | Description | Default |
|---|---|---|---|
| condition | Yes | ||
| user_context | No | ||
| duration_weeks | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true and openWorldHint=false. The description adds meaningful behavioral context by enumerating the protocol's output components (therapeutic foods, meal structure, foods to minimize, monitoring markers, clinical citations), which helps the agent anticipate the result. It does not mention error handling but is still valuable beyond 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?
The description is two sentences, front-loaded with the primary action and followed by a succinct list of return items. Every word earns its place with no redundancy or 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?
The description adequately explains the output components in the absence of an output schema, but it leaves gaps in parameter semantics and usage guidance. The user_context object is not explained, and there is no comparison to query_nutrition_topic. For a moderately complex tool, this is functional but not fully complete.
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% and the description provides no elaboration on any of the three parameters. While the condition enum is self-explanatory, user_context is completely opaque, and duration_weeks is only defined by the schema's bounds. The description fails to compensate for the low schema coverage.
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 an evidence-based whole-food plant-based protocol for 47 chronic conditions, with a specific verb and resource. It lists the return content, which differentiates it from a general nutrition query, though it does not explicitly reference the sibling tool.
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 no explicit guidance on when to use this tool versus query_nutrition_topic, nor does it mention any alternatives or exclusions. The intended use is implied by the description but not stated as a recommendation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
get_protocol is specifically for generating structured protocols for chronic conditions, while query_nutrition_topic handles general nutrition questions. The purposes are clearly distinct with no overlap in expected inputs or outputs.
Both tools follow the verb_noun pattern: get_protocol and query_nutrition_topic. The naming is consistent and predictable, making it easy for an agent to infer tool behavior.
With only two tools, the server feels thin for a domain that could include listing conditions, retrieving specific foods, or managing protocols. However, the narrow focus on protocol generation and Q&A makes the count borderline acceptable.
The two tools cover the main use cases: generating protocols and answering nutrition questions. A notable gap is the lack of a tool to list the 47 supported conditions, which agents would need to discover without guessing. This is a minor workaround but not a critical failure.