Major shareholders of a Japanese company

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

Goes well past the readOnly/openWorld annotations: it discloses that only organisational holders are named while others are aggregated (count and combined ratio), that a missing filing yields status no_public_disclosure rather than an absence of shareholders, that facts are as filed at the basis date and are not an ownership/control determination, and that the route may be disabled in JP-Verify.

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?

Dense but front-loaded: the resource and its source lead, followed by holder-naming, the no_public_disclosure caveat, and the metered-lookup warning. The 'not an ownership or control determination' disclaimers are slightly repetitive but each carries a distinct caveat.

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 and no annotations covering return shape, the description still tells the agent what comes back (named organisational holders, unnamed aggregate with count and ratio, or an explanatory no_public_disclosure status). That is sufficient to interpret a response without the tool schema.

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 the schema already documents both corporate_number (13-digit / T-number) and as_of (YYYY-MM-DD, latest filing on or before). The description's 'by Corporate Number' and basis-date phrasing restates rather than extends that, so baseline 3 applies.

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 (major shareholders / 大株主の状況) and its exact provenance (annual or semi-annual securities report on EDINET, by Corporate Number). This is clearly distinguishable from the sibling verify_* and find_* tools, which are about company identity rather than filed disclosure content.

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?

Usage is implied through the Corporate Number prerequisite and the 'one metered lookup' cost note, but it never states when to reach for this instead of the sibling verify/find tools, nor when-not to use it (e.g. non-Japanese entities). The no_public_disclosure note usefully explains an outcome, not a usage boundary.

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