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

The annotations already declare readOnlyHint=true, so the safety profile is covered, yet the description still adds real behavioral context: one row per policy, ordering by code, a coverage caveat, and an explicit cost of 10 tokens. The ISO 8601 UTC convention with the +9h Japan-time note is practical orientation, though it is boilerplate rather than tool-specific behavior.

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 lead sentence is front-loaded and dense with useful information, but the definition is bloated by a full bilingual restatement of the entire description and a date-format boilerplate paragraph that consumes roughly a third of the text without tool-specific value.

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 9-parameter screen with no output schema and low schema description coverage, the description covers the core filtering semantics and the cost model, but is silent on what 'current' vs 'scheduled' status means and on pagination interplay between limit and offset, leaving an agent to guess at those.

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 description coverage is only 33%, but the description compensates well for the most important parameters by giving the scale ('0-1 decimals', with minDoe 0.03 = 3% in the schema) and by explaining that thresholds are compared with the value or against the lower end of a range. This is semantics you could not infer from the schema alone, though sector, status, limit, and offset receive no coverage.

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 names a specific verb and resource: screening verified dividend policies of actively listed Japanese companies, plus a clear scope boundary of one row per policy ordered by code. It does not explicitly name a sibling such as get_dividend_policy or get_dividends as the alternative, so the boundary is implied 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?

The filter dimensions (policy type, DOE/payout thresholds) imply when to reach for this tool, and the caveat 'A company not listed may simply not be covered yet' usefully frames results. However, it never states when to use this screen instead of get_dividend_policy or get_dividends, and there are no exclusions or prerequisites.

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