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

Although annotations already say the call is read-only and idempotent, the description adds meaningful behavioral context: it is not produced every 4 hour, stale is tripped only after >72h with weekday-only pipeline details, and all market_context values are point-in-time snapshots of a specific execution run. These details go well beyond the annotations and materially affect how an agent should interpret results.

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 longer than typical descriptions, but its length is justified by the two distinct analyses, the many key output fields, and the important caveats. It is well orgized and puts the core purpose first. Some disclaimerminal lines (For informational purposes only) are less actionable for an agent, so it does not get a perfect score.

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?

The description covers when to use each perspective, how staleness works, the cost/tier caveat, the difference between live and point-in-time data, and gives meaning for each major result field. There is also an output schema, so the response format is available elsewhere. This is complete for safe and correct invocation.

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 only parameter is history_count, and the input schema already provides a clear default, a range, and a human-readable description. The tool description repeats this same information but does not add any deeper parameter behavior e.g., navg except the schema already covers it. Baseline 3, as 100% of the schema is described.

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 immediately says this is a combined AI market assessment returning both macro regime and market outlook, which is a specific and distinct resource. It also breaks down the two perspectives into the questions they answer, making the tool's purpose unambiguous and able to be selected from a list.

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 direct usage guidance: the REGIME perspective is for position sizing and asset allocation, and the OUTLOOK perspective is for sector preference and directional bias. It also explicitly says to use get_market_pulse for live data instead of the point-in-time snapshot here, which is a clear when-not/alternative instruction.

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