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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety profile is fully covered. The description adds genuinely useful context beyond that: the data is sourced from the most recent annual report (사업보고서), which tells the agent about freshness and origin, and it discloses that executive data is limited to registered executives. It does not discuss pagination, response size, or latency, which keeps it below 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?

One dense but well-ordered sentence front-loads the product, domain, and data source, then lists contents, and closes with trigger questions. Every clause carries information an agent can use; there is no filler or repetition.

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 two-parameter read tool with full annotation coverage and no output schema, the description covers source, scope, field-level contents, and trigger scenarios thoroughly. The only gap is that it does not indicate the shape of the response (e.g., whether sections come back as separate blocks), which an agent must discover by calling.

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% with both parameters documented, including the enum values and the 'omitted means all three' default, so the baseline is 3. The description enumerates what content lives in each of audit/executives/employees, which helps interpret the section enum, but it never maps those contents explicitly to the section values.

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 names a specific data domain (audit, executives, employees from the latest annual report) and enumerates the exact fields returned — auditor, audit opinion across three periods, KAM, audit fees, executive roster attributes, headcount/tenure/salary. That is far more specific than the bare name 'governance' and clearly separates it from siblings like shareholders or financials. It stops short of an explicit verb or a named sibling it is not, so it lands just under the top mark.

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?

Four concrete example questions ('did the auditor change', 'audit opinion', 'this company's salary', 'who are the registered executives') give a clear picture of when to reach for this tool. There are no explicit exclusions or pointers to alternative tools (e.g., shareholders for ownership questions), so it is clear context without routing rules.

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