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

Annotations only declare readOnlyHint, and the description substantially exceeds that: it discloses the 10-token cost, the 93-day window cap, result ordering, the fact that busy days exceed 2,000 rows, and the exact pagination recovery step. It also resolves timezone behavior (from/to in JST, date-times in UTC with a +9h conversion note), which is real operational context an agent would otherwise get wrong.

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?

Front-loaded with the core purpose, window cap, cost, and pagination recovery before the formatting details each sentence earns its place. The cost is that every point is stated twice in English and Japanese, which roughly doubles length for an agent reading only one language, though the duplication appears intentional for a Japan-market tool.

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, five-parameter list tool with no output schema, the description covers the window cap, ordering, filtering, pagination, token cost, and date/time formatting, which is everything needed to call it correctly. The only minor omission is the limit parameter's behavior.

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 80%, and the description adds meaning the schema lacks: from/to are Japan-time dates and date-time fields return UTC. It also contextualizes symbol (one company) and offset (next page after truncation). The one gap is limit, which has no description in either the schema or the description.

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?

States a specific resource and scope: 'Upcoming/past ex-dividend dates across the whole market within a date window', plus ordering ('ex-dividend date then symbol') and a per-company mode. This clearly separates it from per-company dividend tools, but it never names the closest siblings (get_dividends, get_dividend_changes, get_earnings_calendar), so the agent must infer the boundary itself.

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?

Gives concrete usage conditions: pass symbol for a single company, omit for market-wide, and re-call with the given offset when the result reports more rows. However, there is no explicit 'use X instead when...' routing against the sibling dividend tools, so the when-not-to-use side is absent.

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