evidence_betweenDirect curated relations between two entities (either direction) with full cards for the supporting and conflicting studies. Answers questions such as "what is the evidence that A acts on B?".
| Name | Required | Description | Default |
|---|---|---|---|
| a | Yes | ||
| b | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint=false), so the bar is lower. The description still adds genuine context: retrieval is direction-agnostic ("either direction") and the payload includes full study cards split into supporting and conflicting evidence, which is meaningful given there is no output 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?
Two sentences, purpose front-loaded, no filler. There is mild overlap between the opening clause and the embedded example question, but the structure is efficient.
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?
No output schema exists, so the description does some of the work by naming the returned supporting/conflicting cards, but it omits input identifier format and any cardinality/pagination behavior. For a two-parameter evidence lookup this is adequate but leaves gaps an agent would need to guess around.
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 0% for the two parameters a and b, so the description must carry the burden. It implies a and b are two entities whose order does not matter, but it never specifies the identifier format (name vs. CURIE vs. internal ID) or what distinguishes the two slots, leaving a real gap.
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 and resource: it returns direct curated relations between two entities, plus their supporting/conflicting studies. It does not distinguish itself from the sibling tools find_relations or get_relation, which look closely related, so an agent cannot fully disambiguate among them from the text alone.
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?
Usage is only implied through the example question "what is the evidence that A acts on B?", which conveys the flavor of a query but names no alternative or exclusion. Nothing tells the agent when to prefer this over find_relations or find_contradictions.
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.