프로그램매매 동향 조회

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

Beyond the readOnly/openWorld annotations it discloses the failure mode (400 unsupported-market), the measurement universe (KRX only, NXT excluded), the unit (integer share counts), the netBuyVolume = buy − sell sign convention, the absence of a value/amount axis, and intraday refresh behavior before market close. These are exactly the traits an agent cannot infer from structured fields.

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?

A short lead sentence states the action and the time-series shape, then bullet points carry constraints and pagination, with bold labels for timeliness and rate limits. Dense but front-loaded and scannable. Minor redundancy between the first sentence and the second, which restate the daily-series framing.

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?

There is no output schema, so the description must describe returns itself, and it does: the arbitrage/nonArbitrage buckets, the netBuyVolume semantics, and the `nextUntil` continuation field are all named. Combined with the market coverage, units and refresh caveats, an agent has enough to call and page through this correctly; the undescribed `count` parameter is the only notable gap.

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 carry the parameters, and it only partly does. It explains `until` well as the cursor taken from the previous response's `nextUntil`, but `count` is never described (no meaning, no default, only the schema's 1–100 bounds) and `symbol` gets no format guidance beyond being a KR ticker.

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 verb+resource (program-trading trend lookup) and specifies the shape of the result: a daily volume time series for a KR stock, split into arbitrage and nonArbitrage buy/sell/net volumes, newest first. That scope clearly separates it from siblings like toss_get_stock_investor_trading, toss_get_stock_short_selling and toss_get_stock_credit_trades, which cover different flow dimensions.

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 gives explicit boundaries: KR-only (other markets return 400 unsupported-market), KRX trades only with NXT excluded, and no monetary axis. That is clear context for when this tool applies. It never names a sibling alternative or says what to use when the caller actually wants amount-based or NXT-inclusive data, so it stops short of full routing guidance.

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