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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the bar is lower; the description nevertheless adds real behavioral context by defining the data window (2010 onward), the statistical nature of the output, and the 'counts of past days only, not a forecast' framing. It does not discuss cost, caching, or failure modes, but for a zero-argument read-only counter that is a minor omission.

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 core is front-loaded ('Counts the rainbow chart's past'), but almost the entire definition is a single ~130-word sentence dense with nested parentheticals listing return fields. It would be far more scannable as a short purpose line plus a bulleted list of computed statistics.

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?

With no output schema and no parameters, the description carries the full burden of explaining return content, and it does so comprehensively: every statistic returned is named along with its unit (percent) and accompanying dates or runs. Nothing an agent needs to decide to call or interpret the result is missing.

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?

There are zero parameters and the schema is empty, so there is no parameter meaning to convey; baseline for a no-param tool is 4. The description correctly implies the tool is parameterless by describing fully self-determined output.

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: 'Counts the rainbow chart's past, day by day, from the full price record since 2010', and enumerates the exact statistics produced (highest band ever reached, largest deviation from the trend line, day counts per band, time since last top/bottom band close, today's percentile). An agent can separate this from rainbow_today (today's reading) and cycle_check without opening a schema.

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?

It names the trigger phrases directly ('ever', 'has it ever', 'when was the last time', 'how long did it spend', the highest band ever) and states explicit exclusions: 'not odds, not a forecast, not advice'. The scope boundary 'Counts of past days only' further routes callers away from predictive siblings.

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