TRACE ONE CLAIM to its source: provenance, PubMed verification, same-cohort claims that do not count as replication, counter-evidence and linked hypothesis.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Evidence claim id. |
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | The answer. Shape depends on the tool; describe_tool documents it. | |
| _meta | No | source, generatedAt, sources (per-source lastSyncedAt and ageHours), rateLimit, disclaimer. |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": {},
+ "properties": {
+ "_meta": {
+ "additionalProperties": {},
+ "description": "source, generatedAt, sources (per-source lastSyncedAt and ageHours), rateLimit, disclaimer.",
+ "propertyNames": {
+ "type": "string"
+ },
+ "type": "object"
+ },
+ "data": {
+ "description": "The answer. Shape depends on the tool; describe_tool documents it."
+ }
+ },
+ "type": "object"
+}Input schema / properties / id / maxLengthAdded value: +20000Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real value by disclosing the return contents and a methodological caveat — same-cohort claims do not count as replication — which an agent could not infer from annotations or 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?
Single sentence, front-loaded with the core action, then a compact enumeration of outputs. No filler, no restatement of the tool name's boilerplate.
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?
With an output schema present, the description needn't explain return shape, and annotations cover safety and world-boundedness. It still supplies the essential framing (single-claim, source-of-truth trace with a replication caveat), leaving only minor gaps such as what happens on an unknown id.
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% with a single 'id' parameter documented as 'Evidence claim id'. The description only reinforces cardinality ('one claim'), adding nothing about id format, source, or lookup behavior. Baseline 3 is appropriate.
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?
Specific verb plus resource ('TRACE ONE CLAIM to its source') and the enumeration of what the trace yields (provenance, PubMed verification, counter-evidence, linked hypothesis) makes the operation concrete. Scope is scoped to a single claim, implicitly distinguishing it from list/search siblings, though no sibling is named.
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 singular 'ONE CLAIM' implies this is a per-claim deep dive rather than a discovery tool, but there is no explicit statement of when to use it over get_finding, find_evidence_contradictions, or search_cure_evidence. Usage must be inferred from the scope wording.
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.