build_timeline_state

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose key behaviors: aggregation, deduplication, derived field computation, and phase determination. However, it doesn't disclose what happens to conflicting events during deduplication, whether the input events are mutated, or what the output structure looks like. The description adds value but leaves important behavioral details 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, front-loaded with the primary purpose and followed by specific operations. Every sentence earns its place. It's concise and structured well, though it could arguably be more explicit about usage context.

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 tool with 2 parameters, no output schema, and no annotations, the description covers the main operations but leaves gaps: no output format description, no mention of error conditions (e.g., empty events array), no details on how duplicates are resolved. The sibling tools suggest a pipeline context, but the description doesn't fully situate this tool within that pipeline.

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 description coverage is 50%: reference_time has a description, but events does not. The description mentions 'events' and 'reference_time' implicitly through 'extracted events' and 'days_since_surgery' (which requires reference_time), but it doesn't add detail about the events array structure or how reference_time is used beyond the schema. The description partially compensates for the schema gap but doesn't fully explain the relationship between the two parameters.

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's purpose: creating a normalized timeline state from extracted events. It lists specific operations (aggregates events, resolves duplicates, computes derived fields, determines recovery phase) that distinguish it from siblings like extract_timeline_events or summarize_timeline_context. However, it doesn't explicitly name a sibling to differentiate from, so it loses a point.

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 usage context: it takes extracted events and produces a normalized state, which suggests it should be used after extract_timeline_events and before summarize_timeline_context. However, it doesn't explicitly state when to use this tool versus alternatives like upsert_message_into_timeline or days_since_event. The usage guidance is implied but not explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.