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

Annotations already declare readOnlyHint=true, so safety is covered; the description goes beyond that by disclosing that corrections are collapsed to the latest version and that unlisted-filer history is partially backfilled via a coverage field, plus the 93-day maximum window. That is genuine behavioral context an agent could not get from the annotations or schema. It stops short of describing ordering or what the coverage field actually looks like.

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 core content is front-loaded and useful, but the entire description is duplicated in Japanese, including the ISO 8601 formatting explanation and the JST clarification, which roughly doubles length without adding new information for a reader who already parsed the English. The structure is otherwise scannable and every English sentence carries content.

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 six-parameter, no-output-schema read tool, the description covers what matters: the entity and fields returned, correction collapsing, three filter axes, the window cap, and a data-coverage caveat with a pointer to the coverage field. Missing only return ordering and whether 'each holder' breakdown is affected by includeHolders, both minor.

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 67%, so the baseline is 3. The description does add real meaning: from/to are JST dates while other date-times are ISO 8601 UTC, the from/to range is capped at 93 days, holder is the filer's EDINET code, and symbol is the issuer ticker. It gives no semantics for limit or includeHolders, so it only partially compensates for the coverage gap.

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 opens with a concrete question ('Who crossed or changed a 5%+ stake?') and identifies the resource precisely: EDINET large shareholding and change reports, retrieved one filing at a time, with the specific fields returned (filer, issuer, filing date, change reason, holding ratio now vs previous). It does not, however, name or distinguish itself from the sibling tools get_large_holders and get_major_shareholders, which are the obvious alternative sources of holder data, so an agent must infer the difference.

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 description gives clear filtering options ('Filter by issuer symbol, filer EDINET code (holder) or a from/to window (max 93 days)'), which implies usage, and it warns that historical filings by unlisted filers are still being backfilled 'see the coverage field'. But it never states when to choose this tool over get_large_holders or get_major_shareholders, and there is no explicit when-not guidance.

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