track_market_reaction

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

The description discloses important behavioral traits: it does not generate scores/ratings, avoids threshold/judgment vocabulary, only reports factual metrics. It also explains data source fallback behavior. However, it doesn't mention rate limits, auth requirements beyond API keys, or what happens when no data is found. Still, the behavioral disclosure is substantial.

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?

The description is well-structured with clear sections: purpose, data sources, behavioral constraints, and parameter explanations. It is somewhat long but every section earns its place. The parameter list is front-loaded with the most important info. Minor redundancy in the 'no scoring' emphasis, but it's important for correct usage.

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 tool's complexity (6 params, multiple data sources, parameter precedence), the description covers most of what an agent needs. It explains the output philosophy (no scores, only facts) and the data source logic. The main gap is the undocumented lookback_days parameter and lack of explicit output format description, though the output schema exists. Overall quite complete.

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 carries the full burden. It explains company_name (name or 6-digit code), lookback_years (default 1, range 1-5, ignored if rcept_no given), from_date/to_date formats, and rcept_no behavior (10 trading days around the filing). It does not mention lookback_days, which appears in the schema but not the description, creating a minor gap.

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 clearly states the tool's purpose: it tracks market reaction around disclosures (KRX/KIS price data, KIND market alerts) and explicitly says it does not assign scores/ratings. It distinguishes itself from sibling tools by focusing on market price/volume/turnover movement around disclosures, not risk scoring or insider trading.

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 explicitly explains when to use this tool: when you need to know how the market reacted before/after a disclosure, and it contrasts with DART-only knowledge. It also specifies data source priority (KRX first, KIS fallback) and parameter precedence rules (rcept_no overrides lookback_years/from_date/to_date). This is strong usage guidance.

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