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

Annotations only supply readOnlyHint, and the description goes well beyond it: data starts in 2013, zero-dividend years break the streak, values are split-adjusted, ETF/REIT figures use calendar-year totals (two periods for a semiannual J-REIT), and the capped flags mean the streak reached the first year of the series. The meaning of capped=true as a lower bound ('N years or more', never set for 0) is exactly the kind of subtle behavior an agent would otherwise misread.

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 answer to the core question is front-loaded and every English sentence carries substantive information (streak definitions, 2013 cutoff, capped semantics, ETF/REIT handling). The main cost is the full Japanese restatement, which duplicates content and roughly doubles length, plus the parenthetical-packed final sentence.

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 a readOnly annotation, the description carries the return-shape burden and does so: it names the fields returned and explains the capped sentinels. Minor gaps remain — currency/units for the per-share amounts and the exact ordering/shape of the per-fiscal-year list are not spelled out.

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 coverage is 100% and both parameters are documented in the schema, so the baseline of 3 applies. The description adds context for the returned per-year dividend values but says nothing extra about limit semantics (newest-first ordering, max 25) beyond what the schema already states.

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?

Opens with a concrete framing question and then names the returned fields (consecutive-increase years, consecutive-non-decrease years, annual dividend per share per fiscal year). That clearly separates it from raw-history siblings like get_dividends or get_dividend_changes, but no sibling is named explicitly, so the differentiation is inferred rather than stated.

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?

Usage is implied by the 'how many years in a row...' framing, which tells an agent this is the streak-summary tool rather than the raw dividend series. However, there is no explicit statement of when to prefer it over get_dividends / get_dividend_changes / get_dividend_policy, and no prerequisites or exclusions are given.

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