get_shareholders

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

With no annotations provided, the description carries the burden of disclosing behavior. It usefully explains what kind of data is returned (5%+ stake reports, ratio, as-of date) and that this is the issuer-side filing view. However, it does not mention whether the result is a list, how the data is ordered, or any pagination or time-range limitations, leaving some behavioral ambiguity for an AI agent.

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?

Two tightly written sentences deliver the core purpose, the threshold, the data content, and the sibling distinction. The most important scoping information is front-loaded in the first sentence, and every clause adds value with no filler.

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?

Given the low complexity of a single-parameter getter, the description is nearly complete: it tells the agent what will be returned, what threshold applies, and how this differs from search_shareholders. The absence of an output schema and annotations means some return-format specifics are not covered, but they are minor for this tool's simple usage.

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?

The input schema already documents the single parameter very well, including that it requires an EDINET code, provides concrete examples, notes that it is not a securities code, and points to search_companies for resolution. Since schema description coverage is 100%, the tool description itself adds little new parameter-level meaning beyond tying the code to a single company context.

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 states a specific verb and resource: retrieving large-shareholding reports for a company, with the 5% threshold and key data points (ratio and date). It explicitly distinguishes itself from its sibling search_shareholders by framing this as the issuer-side view, so there is no ambiguity about scope.

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 clearly explains when to use this tool versus search_shareholders: use it to see all declared stakes against one company, and use search_shareholders to see everything one investor holds. The parameter description adds a concrete prerequisite: resolve names or securities codes to an EDINET code with search_companies first.

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