pulse_cohort_bias_history

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

No annotations are provided, so the description must carry the full burden. It states that the tool is read-only ('Get historical...'), is hourly aggregated, has a 30-day max range, and supports per-coin or aggregate. However, it doesn't mention rate limits, data freshness, or any destructive behavior, but for a historical data retrieval tool, the description is adequate.

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 three sentences, each adding distinct value: first sentence defines the tool's output, second explains its purpose and cohorts, third lists key parameter options. No fluff, all relevant information front-loaded.

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 the moderate parameter count (5) and simplicity of the tool (historical data retrieval without nested objects), the description covers its purpose, usage, and key behavioral traits well. No output schema is present, but the return value is described at a high level (net long/short notional and counts per tier), which is sufficient for an agent to understand what to expect.

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 100%, so the description's job is to add context. It does so by explaining the coin parameter's dual usage (omit for aggregate, prefix for builder dex), the since parameter's format and max range, and the useToonFormat parameter's default and alternative. This adds meaningful guidance beyond the schema.

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 identifies the tool as retrieving historical hourly bias snapshots for trader cohorts, specifying the return type (net long/short notional and account counts per tier) and mentioning coin or aggregate filtering. This distinguishes it from siblings like 'live_cohort_bias' (current) and 'pulse_cohort_history' (non-specific).

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 explicitly states when to use the tool (to see how cohorts' positioning shifted over time) and the maximum range (30 days). It doesn't explicitly say when not to use or alternative tools, but the purpose is clear enough that an agent can infer it's for historical hourly bias, not real-time or daily granularity.

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