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

With readOnlyHint=true already declaring the safety profile, the description adds genuinely useful behavior: record ordering differs depending on whether from/to is present, limit truncation emits a continuation hint, and same-ex-date rows are grouped so a call may exceed limit (with a concrete 7203 example). However, this is the strongest area and it still omits error behavior for invalid tickers and any indication of response envelope shape beyond the field list.

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 purpose is front-loaded and the substantive content (ordering, continuation, grouping overshoot, timezone) all earns its place. But the entire description is duplicated in Japanese and the timezone/format rules are restated twice even within the English text, roughly doubling length for an agent that needs only one pass.

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 read-only, 4-parameter list tool with no output schema, the description covers ordering, pagination continuation, grouping edge cases, and date/time formatting thoroughly. The remaining gap is sibling disambiguation and failure behavior, which are relevant given the many neighbouring dividend tools.

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?

At 75% schema coverage the description goes well beyond the schema: it clarifies that from/to filter on ex-dividend date (inclusive) in JST while the schema only says 'earliest/latest ex-dividend date', and it explains the interaction between limit and same-date grouping that can push a response past the limit. The undocumented limit parameter's default (40), maximum (100), and overshoot behavior are all covered.

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 first sentence states a specific resource (dividend history) and enumerates the exact fields returned (ex-dividend date, payment date, announcement date, split-adjusted amount, forecast/actual), so an agent knows precisely what data it gets. It does not, however, distinguish itself from close siblings such as get_dividend_changes, get_dividends_calendar, or get_dividend_streaks, leaving that discrimination to the caller.

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 gives clear operational context: call without from/to for the newest records, pass from/to for older periods, and expect a continuation 'to' value in the response only when from/to were supplied. It does not state when this tool should be preferred over the sibling dividend tools, so it stops short of full alternative routing.

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