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

readOnlyHint already covers safety, so the description's job is added behavior — and it does add real substance: the data source, the temporal scope ('latest annual securities report'), the ownership-ratio scaling (0.0774 = 7.74%), and the non-obvious rule that joint holders under 5% each appear on their own row. It omits ordering and whether non-reporting issuers yield an empty set, which keeps it from a 5.

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 English content is front-loaded and useful, but the definition is roughly tripled by a full Japanese restatement of every sentence plus a generic ISO 8601/UTC boilerplate block ('add 9 hours for Japan time') that is boilerplate rather than tool-specific guidance. The core facts survive trimming, so length costs it here.

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 only two parameters and no output schema, the description carries the return-value burden and does it: it enumerates the returned fields (holder name, shares, ownership ratio, source document) and pre-empts the ratio-format confusion. What is missing is coverage/edge behavior — no data for non-reporting issuers, and the undocumented meaning of the total row.

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 100%, so both `symbol` (with a Toyota "7203" example) and `includeTotal` are already documented; baseline 3 applies. The description adds no meaning for `includeTotal` — notably it never explains what the 'total' aggregate row contains or when to request it — so it does not exceed the schema.

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 threshold (holders of 5%+) and pins down the exact source table (large-shareholding-report reference table in the latest annual securities report), plus the fields returned. It explicitly distinguishes itself from get_major_shareholders (top-10 table), so an agent can pick between them 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 clear context for selection by saying it 'complements get_major_shareholders (top-10 table)' and noting the Japanese equivalent (大株主本表とは別の参考表), which tells the agent this is a different table, not a different filter. It stops short of an explicit when-to-use/when-not rule, and it does not distinguish itself from the similarly named sibling get_large_holding_reports.

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