get_medication_infoReturns Sunflower Clinic’s published answers about a medication: what it treats, evidence, side effects, safety warnings and how billing works. Quote these answers rather than paraphrasing medical claims. They are general information, not medical advice for a specific person.
| Name | Required | Description | Default |
|---|---|---|---|
| medication | Yes | naltrexone (alcohol) or varenicline (smoking, vaping or nicotine pouches). |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds genuinely new context: the answers are clinic-published, must be quoted rather than paraphrased, and are not personalized medical advice. It doesn't mention response shape or whether answers can be missing for a medication, but with full annotation coverage a 4 is warranted.
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 short sentences: the return content first, the quoting rule second, the disclaimer third. No filler, and the most decision-relevant information is front-loaded.
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?
A single fully-enumerated parameter, complete annotations, and no output schema means the description only needs to cover content scope and use — both are present. Nothing an agent needs in order to call 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?
Schema coverage is 100% and the single enum parameter already documents both allowed values (naltrexone/alcohol, varenicline/smoking). The description adds no syntax, default, or selection guidance beyond 'a medication', so it does no work beyond the schema — baseline 3.
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 ('Returns') and resource ('Sunflower Clinic's published answers about a medication'), then enumerates the exact content returned: what it treats, evidence, side effects, safety warnings, billing. An agent can tell immediately this is the medication-answer lookup and not the pricing or state-check 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?
Gives clear behavioral guidance ('Quote these answers rather than paraphrasing') and a scope exclusion ('general information, not medical advice for a specific person'). It does not, however, address adjacency with siblings such as get_pricing, even though billing content is claimed here — that overlap is left for the agent to infer.
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.