Extract timeline-relevant events from conversation messages by parsing time expressions and detecting medical events like surgeries, medication changes, and follow-ups.
Extract timeline-relevant events from a list of conversation messages. Parses time expressions and detects event types like surgery, stitch removal, symptom start, medication start/stop, and follow-up visits.
| Name | Required | Description | Default |
|---|---|---|---|
| messages | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose core behavior: parsing time expressions and detecting event categories, and 'extract' implies a non-mutating operation. However, it does not state whether input is modified, what the output looks like, or any limitations, which leaves some behavioral detail unspecified.
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 with no filler. The core purpose is front-loaded, and the second sentence adds useful detail about parsing behavior and event types without repeating schema information.
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 one-parameter extractor, the description covers the input and the extraction behavior quite well. However, it omits the expected output shape and the integration point with sibling tools such as build_timeline_state. It is minimally viable but not fully self-sufficient for an agent deciding how to chain these timeline tools.
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?
With only one parameter, the schema already defines the messages array structure and the ISO-8601 timestamp field. The description adds that the input is a list of conversation messages and that time expressions in them are parsed, which helps connect the parameter to the tool's behavior. It does not explain the role of 'id' or further elaborate on timestamp semantics, but the description partially compensates for low schema coverage.
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 uses a specific verb ('extract') and a clear resource ('timeline-relevant events from a list of conversation messages'), and it enumerates concrete event types such as surgery, stitch removal, and medication start/stop. It does not explicitly contrast with sibling tools, but the extraction framing is distinct from build, summarize, days_since, and upsert.
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 gives no guidance on when to use this tool versus its siblings. Given that build_timeline_state, summarize_timeline_context, days_since_event, and upsert_message_into_timeline exist, the description should state that this is the preprocessing extraction step and what the alternatives are for. Usage is only implied by naming the input.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.