连板评分实证校准

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

With no annotations provided, the description carries the full burden and does well: it discloses network dependency, computational weight, and side effects by specifying that results are written to data/score_calibration.json and reports.db with rtype=score_calibration. It also notes the output is intended for limit_up_scan adoption. It does not mention overwrite behavior or failure modes, but the key behavioral traits are covered.

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 a single dense sentence that front-loads the core action and then adds side effects and usage timing. Every clause earns its place with no filler. It is somewhat packed with technical jargon, but remains appropriately sized for a complex calibration tool.

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?

The tool is complex, has no output schema, and no annotations, so the description needs to explain both return behavior and integration points. It covers the data source, methodology, outputs, and runtime constraints well. However, it does not describe what the tool returns to the caller (e.g., a success summary or metrics), nor does it route the agent to limit_up_calibration_latest for inspecting the stored results.

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 0%, so the description must compensate. It does so by explaining that the tool pulls the recent N trading days, which maps naturally to the single 'days' parameter and clarifies that N is trading days, not calendar days. It adds meaning beyond the bare integer schema, though it does not state allowed ranges or effects of larger 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 clearly states the tool's function: pulling real limit-up pool data, constructing continuation labels, computing AUC/group success rates, and outputting data-driven weights. It names the downstream consumer (limit_up_scan) and the files/database written, making the purpose concrete and distinguishable from typical data-query siblings. It does not explicitly differentiate against limit_up_calibration_latest, so it stops short of a 5.

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 gives clear operational context: requires network, is heavy, and is recommended to run after market close. This tells an agent when it is appropriate to invoke the tool. It does not explicitly name alternatives or state when not to use it, such as pointing to limit_up_calibration_latest for reading existing calibration results.

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