pulse_cohort_history

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

The description discloses that the tool returns day-by-day aggregate data for a cohort, which is useful. However, with no annotations, it does not cover data freshness, pagination, rate limits, or potential missing data scenarios. It provides basic behavioral context but is not exhaustive.

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?

Two succinct sentences convey the tool's purpose, output, and a usage example. No redundant information; every sentence adds value. Highly front-loaded and efficient.

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 4 parameters and no output schema, the description adequately explains what the output contains (daily aggregate PnL, trade count, activity). The useToonFormat parameter hints at output format. However, it could be more precise about the data structure (e.g., time series format, units).

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?

The description adds meaning beyond the schema by explicitly listing the returned metrics (PnL, trade count, activity) and tying them to the tier and tierType parameters. The schema covers 100% of parameters, but the description clarifies the output nature, aiding agent selection.

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 it retrieves historical performance data for a specific trader cohort, detailing the metrics (aggregate PnL, trade count, activity) and providing a concrete usage example ('smart_money has been increasingly bearish'). This distinguishes it from sibling tools like pulse_cohort_bias_history or pulse_cohort_performance_daily.

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 for spotting trends over time with an example, but does not explicitly outline when to use this tool versus alternatives like pulse_cohort_bias_history or pulse_cohort_summary. The example provides context, but lacks clear 'when not to use' guidance.

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