episodes

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds some behavioral context: results are timezone-aware, grouped into temporal groups, and include source lanes and evidence, and there is a budget-related constraint. However, 'budget' is undefined, and the description does not clarify ordering, pagination, or how grouping thresholds like gap_seconds/max_span_seconds affect behavior.

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 short and the main concept is placed first, which is good. However, it relies on unexplained jargon ('source lanes', 'evidence', 'budget') and the final sentence is more of an imperative than a clear specification. It is concise but not optimally structured for comprehension.

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?

This is a 12-parameter tool with no output schema and no per-parameter descriptions, so the description carries a large burden. It does not explain return shape, pagination, parameter semantics, or how the grouping thresholds work. An agent cannot reliably call this tool correctly from the provided definition alone.

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 0%, so the description must compensate for 12 undocumented parameters. It only hints at a time window (start/end) through 'timezone-aware window' and at a limit concept through 'budget', but it does not explain kind, fidelity, profile, source_id, project_id, provenance, gap_seconds, max_span_seconds, or cursor. This is far below what is needed for an agent to choose and fill parameters correctly.

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 identifies a distinct resource ('temporal groups within a timezone-aware window, with source lanes and evidence') and explicitly excludes dwell time and causal links, which gives some conceptual separation from siblings. However, it lacks an explicit verb like 'return' or 'list', and 'temporal groups' is vague without knowing the domain. It does not clearly differentiate from similar sibling tools like timeline or project_timeline.

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 one actionable usage rule: narrow the window if a budget is exceeded. It also negatively scopes the tool by saying it is not dwell time or causal links, which helps avoid misuse. But it does not state when to prefer this tool over siblings such as timeline, query, or project_timeline, nor does it describe prerequisites or contexts where this tool is the right choice.

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