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

Annotations only declare readOnlyHint=true, and the description adds real value on top: the data source (latest EDINET filing), the row granularity (one row per holder), the exact returned fields, the ownership-ratio normalization (0-1 decimal with a concrete example), and the presence of a source-document link. It does not state what happens when no filing exists or whether results are truncated, but the return-shape disclosure is strong for a read-only tool.

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 field enumeration is front-loaded and useful, and the bilingual naming aids Japanese-market users. The closing claim 'This data is not available from competing Japanese data APIs' is marketing that consumes space without helping an agent call the tool, and the field list plus Japanese restatement makes the description longer than necessary.

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 compensates well by enumerating return fields, their units, and the source link. For a simple two-parameter read-only tool the remaining gaps are coverage questions (do all tickers have EDINET filings? how does this differ from get_large_holders?) rather than blockers.

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%, so both `symbol` and `includeTotal` are already documented with examples and defaults, warranting the baseline 3. The description adds nothing about the optional `includeTotal` flag, and its phrase 'one row per holder' arguably understates the aggregate row that flag introduces.

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?

Names the resource precisely (major shareholders, one row per holder) and its provenance (latest EDINET filing), which an agent can map to a concrete result set. However, it never distinguishes itself from the closely-named siblings get_large_holders, get_large_holding_reports, and get_cross_shareholdings, leaving the agent to guess which shareholder tool to pick.

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?

There is no explicit when-to-use or when-not-to-use guidance and no alternative is named. In a sibling cluster containing four other shareholder-related tools plus search_by_shareholder, the absence of routing guidance is a meaningful gap; only the implicit 'get major shareholders for a ticker' reading is available.

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