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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds meaningful behavioral detail beyond that: sampling up to max_sample from the start of the window, disclosure of truncation, and the group-selection mechanism via anchor events and date windows. It does not contradict any annotation and gives the agent a realistic picture of how results are produced.

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 four dense sentences with no filler; the main purpose and example lead, followed by selection logic, output summary, and sampling behavior. It packs substantial information into a compact space, though a slightly more explicit break between concepts could improve scannability.

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?

Given 9 parameters, full schema coverage, and no output schema, the description covers the essential gaps: what the output contains (average, median, percentiles, count of no-start-event marks, examples), sampling/truncation, and the 366-day window cap. It does not detail the exact response structure, but the listed metrics are sufficient for an agent to invoke and interpret results.

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 100% schema description coverage, the baseline is 3, and this description adds value beyond the schema by explaining the conceptual roles of anchor event, start event, and end event, as well as the wildcard semantics for raw event codes. It also clarifies the relationship between sampling and the date window, which the schema does not convey.

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 opens with a specific verb and resource: 'Measures the time between two prosecution events across a group of marks.' It provides a concrete example (average days from Office Action to publication for Q2 2026) and enumerates anchor event presets. This clearly distinguishes it from per-mark tools like get_prosecution_timeline or get_mark_prosecution_summary.

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 intended use is implied by the description: aggregate cohort interval statistics. It explains cohort selection, window constraints, and event code flexibility, but it never explicitly says when to prefer this tool over siblings or when not to use it. The only cross-reference is to get_event_code_reference for event codes, which is auxiliary rather than usage direction.

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