get_evidenceCross-references de autoridade (Orphanet, MONDO, OMIM, MeSH, GARD, UMLS), status de verificação e PMIDs de uma doença. A base da regra "nunca inventar".
| Name | Required | Description | Default |
|---|---|---|---|
| orphaCode | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| pmids | Yes | ||
| xrefs | Yes | ||
| orphaCode | Yes | ||
| diseaseTwin | Yes | ||
| neverInvent | Yes | ||
| verification | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true, and the description adds behavioral context by specifying the exact data sources and the 'never invent' principle, which signals the tool is authoritative and should be trusted for evidence. It does not contradict annotations and adds useful context about the tool's role in grounding factual claims, though it does not mention pagination or rate limits.
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 long, front-loaded with the primary function and followed by a short rationale. Every word earns its place, with no redundancy or 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?
Given the simple input (one required parameter), the presence of an output schema, and the readOnly annotation, the description sufficiently covers the tool's purpose and content. It does not need to explain return structure due to the output schema, and the 'never invent' phrase adds contextual value. The only minor gap is explicit usage boundaries, which is already addressed in the usage dimension.
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 has one parameter, orphaCode, with 0% coverage in the description. The description says the tool returns evidence 'of a disease,' implying the input is a disease identifier, but it does not explicitly explain that orphaCode is the Orphanet code. Since there is only one parameter and its name is self-descriptive, the description provides adequate if minimal semantic guidance.
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 retrieves evidence/provenance for a disease, listing specific authority databases (Orphanet, MONDO, OMIM, MeSH, GARD, UMLS) along with verification status and PMIDs. It distinguishes itself from siblings like get_disease_detail by focusing on cross-references and verification, though it lacks an explicit action verb like 'retrieves' or 'returns'.
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 when to use the tool: it provides authoritative cross-references and is 'the basis of the never invent rule,' suggesting it should be used to ground disease facts. However, it does not explicitly mention alternatives or when not to use it, so guidance is implicit rather than explicit.
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.
Most tools have clear, distinct purposes, but there is a cluster of 'find' tools (find_similar_diseases, find_phenotypically_similar, find_diseases_by_phenotypes) that could be confused; descriptions differentiate them (semantic vs HPO similarity vs exact match), and the paper search tools also differ by input type. Overall, ambiguous pairs are explicitly disambiguated, leaving only a few close calls.
All tools consistently follow a snake_case verb_noun pattern, using a limited set of verbs (analyze, explain, find, get, search) that map predictably to tool functionality. No mixed conventions or vague names are present, making the naming highly systematic.
At 20 tools, the server is slightly above the ideal range of 3-15, but each tool serves a distinct function within the rare disease knowledge platform. The breadth of features—search, similarity, detail, evidence, literature, hypotheses, graph exploration—justifies the count without feeling bloated or redundant.
The tool surface comprehensively covers the rare disease domain: search, differential diagnosis, disease detail, evidence, SUS/trials, reference centers, literature, hypotheses, and graph analytics. Write operations are not expected for a read-only knowledge base, and the inclusion of research log and recent updates closes all apparent gaps.