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

Beyond the readOnlyHint, idempotentHint, and openWorldHint annotations, the description adds substantive behavioral detail: odds are withheld until 60 observed days, counts remain visible, absence is not to be read as precision, and values are not calibrated forecasts. This goes well beyond what the annotations alone convey.

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?

Three sentences, each earning its place: the first states the resource, the second describes data availability semantics, and the third adds critical interpretation caveats. It is compact, front-loaded, and contains no filler.

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 no-argument read-only tool, the description covers purpose, availability thresholds, absence semantics, and forecasting limitations. It does not spell out the exact response shape, but there is no output schema and the core return concept is clear from 'counts' and 'odds'.

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 input schema has zero parameters and 100% coverage trivially, so parameter-level documentation is unnecessary. The description supplies the needed context about what is read and how missing values behave, matching the baseline for a parameterless tool.

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 the specific verb 'Read' and names the exact resource: counted Markov transitions and empirical 5/20-day reach odds. This aligns with the title and is clearly distinguishable from the board/review-style sibling tools, none of which cover the same raw Markov odds output.

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 phrase 'Display-only, never a state driver' gives an explicit when-not-to-use boundary, and 'Historical frequencies are not calibrated forecasts' warns against using the output as a forecast. It does not explicitly name an alternative tool, but there is no close sibling doing the same thing, so the guidance is still clear enough.

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