get_audit_opinion_history

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

With no annotations, the description carries the full behavioral burden. It helpfully discloses a data-availability boundary (the auditor's reasoning is not in the structured response but in the original text) and mentions it aggregates three DART endpoints and emits warning signals. However, it says nothing about auth/permissions, rate limits, or read-only status, so disclosure is incomplete for an unannotated 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?

Front-loaded with the purpose and the sibling distinction, then the endpoint/behavior note, then args. The explicit 'Returns:' section is mildly redundant given an output schema exists, but overall the text is tight and each part earns its place.

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 2-parameter tool with an output schema, the definition covers both parameters fully and explains the behavioral scope. The only gaps are unannotated operational details (safety/limits), which are minor given the output schema and clear param documentation.

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 0%, so the description must compensate, and it does: company_name is documented as accepting either a company name or a 6-digit ticker, and lookback_years as a 1–10 range that is clamped to 5 when out of bounds. This adds real semantics (accepted formats and clamping behavior) beyond the bare 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 verb (조회) and a precise set of resources (감사의견·감사인 교체·비감사용역 이력), then explicitly distinguishes itself from the sibling get_audit_opinion_text by noting that tool quotes the auditor's narrative reasoning from the original text. An agent can pick between the two 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?

It clearly routes the agent: use this for the year-by-year opinion/auditor-change table, and use get_audit_opinion_text when the auditor's written reasoning (opinion basis, going-concern uncertainty, emphasis, key audit matters) is needed. Context for use is explicit, though there is no stated 'when not to use' beyond the sibling routing.

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