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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: it aggregates over a 3-year disclosure window and returns a 5-tier grade (낮음~위험) with supporting rationale, telling the agent what shape the answer takes. It omits any note on data freshness, latency, or what happens for unlisted/unknown tickers.

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-loads the server tag, tool name, and core verdict, then packs the signal list and output shape into the remainder. The long enumerations of risk criteria are dense but each clause carries information an agent needs to judge relevance; a small amount of the management-designation detail could be trimmed.

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, the description must explain the return value and does so explicitly (5-tier grade plus 근거/evidence). Given a single fully-documented parameter, the lookback window, the signal set, and the answer format, an agent has everything needed to call it and interpret the result.

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?

Only one parameter, and the schema already documents it at 100% coverage including both accepted formats (6-digit code or company name with examples). The description adds nothing further about the stock argument, so the baseline 3 for fully-covered schema 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 verb (점검/assess) and resource (a company's financial risk), then enumerates the exact signal families covered: capital impairment, consecutive operating losses, debt ratio, interest coverage, operating cash flow deficit, price collapse, plus a 3-year disclosure-history scan. This is clearly distinguishable from siblings like financials, disclosures, or governance, which return raw data rather than a synthesized risk verdict.

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 concrete trigger questions ('이 회사 위험해?', '상장폐지 징후', '재무 안정성'), which is strong positive routing guidance. It does not, however, say when to prefer a sibling instead — e.g. that financials gives raw statements or disclosures gives filing lists — so the negative side of the decision is left implicit.

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