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

Annotations only declare readOnlyHint, and the description adds real behavioral context: the 2026-05-18 detection cutoff, what a null changeFlag means and that such rows are excluded when filtering, and a stated cost of 10 tokens. It does not describe pagination/limit behavior across the 500-row cap, so it falls short of full disclosure.

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, but the entire text is duplicated in Japanese, roughly doubling length, and the date-format guidance is repeated twice within the English portion. The information is useful but the delivery is padded.

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, the description names the returned fields (previous vs new dividend, change rate, implied yields, source document) and explains the null-flag edge case. The only gap for a 5-parameter filtered-list tool is pagination/limit behavior near the 500 maximum.

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%, yet the description adds meaning the schema does not carry: from/to are JST dates while timestamps are UTC ISO 8601, symbol omission means whole-market scan, and the null-changeFlag semantics are restated in context. The limit parameter remains undocumented beyond its numeric bounds.

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 verb+resource: annual-dividend revisions detected from TDnet earnings releases, with the fields returned (previous vs new dividend, change rate, implied yields, source document). It explicitly separates itself from the sibling get_dividends by time coverage, so an agent can choose without opening either schema.

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 explicit when-to-use (omit symbol to scan the whole market for a date window), an explicit exclusion (announcements before 2026-05-18 are not included), and an explicit alternative (use get_dividends for older changes) with a concrete example.

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