Get the GRADE-rated evidence summary for one indication (reviewed studies only). Use a slug from list_indications.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Language of the answer and of the cited source URL. 'de' (default) cites mechoulam.de/..., 'en' cites mechoulam.de/en/... | |
| slug | Yes | Indication slug |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true, so no safety contradiction exists. The description adds behavioral value by stating that only reviewed studies are included and that the evidence is GRADE-rated, which tells the agent what kind of content to expect without relying on 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 tight sentences, front-loading the core action and then giving the one essential usage instruction. There is no filler, repetition of schema details, or unnecessary explanation.
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 simple lookup tool with two well-documented parameters, safe read-only annotations, and a clear source of valid slugs, the description covers everything an agent needs to invoke it correctly. The absence of an output schema is mitigated by the phrase 'GRADE-rated evidence summary', which adequately conveys what will be returned.
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 schema already documents both parameters with 100% coverage, so the baseline is 3. The description adds meaningful semantic guidance by telling the agent that the slug should come from list_indications, which is exactly the operational knowledge needed to call the tool correctly.
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 begins with a specific verb and resource: 'Get the GRADE-rated evidence summary for one indication'. It adds important qualifiers ('reviewed studies only') that distinguish this from searching or fetching raw studies. It even points to the sibling list_indications as the source of valid slugs, making the tool's role in the family clear.
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 instruction 'Use a slug from list_indications' gives a clear precondition and points to the correct data source. It does not explicitly enumerate alternatives or say when not to use this tool, but for a single-purpose lookup the context is sufficient.
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.
Search and list_indications are clearly distinct, but fetch overlaps with get_indication and get_study since it also retrieves a full record by ID. The descriptions help somewhat, but an agent could reasonably struggle to choose between the generic fetch and the more specific getters.
list_indications, get_indication, and get_study follow a consistent verb_noun pattern, but search and fetch are one-word verbs that break the convention. The mix is readable but not fully predictable.
Five tools is a well-scoped surface for a read-only evidence register. Each tool covers a necessary part of discovery and retrieval without unnecessary bloat.
The register's core workflow is covered: search across records, list indications, and retrieve detailed indication summaries or individual studies. A minor gap is the lack of an explicit list-studies endpoint, but search and fetch can fill that need in most cases.
