sw_deliver

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

With no annotations, the description carries the full burden of disclosure. It effectively reveals that the tool returns executable code rather than data and that it does not rerun the simulation ('不必重跑仿真'). It also explains the default behavior (only channel if 'want' is omitted). However, it omits details about side effects, authorization requirements, or error handling, which would be valuable for a tool with no structured safety hints.

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 remarkably compact, with three clear sections: core purpose, usage examples for 'want', and a note on reusability. It front-loads the key differentiator (returns Python, not data) and avoids any filler. Every sentence earns its place, making it easy to parse quickly.

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 simple interface (2 parameters) and its focus on code generation, the description covers the essential aspects: what it returns, how to customize with 'want', defaults, and the critical fact that no simulation rerun is needed. There is an output schema, so return value details are not necessary. It could mention how to obtain a valid dataset_id (e.g., from sw_list_datasets), but overall it provides sufficient context for an agent to use the tool correctly.

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?

The schema has 0% description coverage, so the description must compensate. It does this well for the 'want' parameter by providing natural language examples ('信道', '信道 + PMI + SRS RSRP', '我还想看时延功率谱') and clarifying the default (only channel). The 'dataset_id' parameter is not elaborated, but the description references it as an identifier for an existing dataset, which gives partial context. This is strong compensation for a 2-parameter schema.

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 generates runnable Python code on demand, explicitly contrasting with returning data ('不是数据'). It specifies the scope (from a dataset) and the main verb (generate), which distinguishes it from sibling tools that likely execute simulations or manage datasets. However, it doesn't name alternative tools, and '取货代码' is a slightly metaphorical term, so not 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?

It implies usage when you need specific measurement quantities from an existing dataset without re-running simulation, and explicitly notes that the same dataset can be repeatedly used for different metrics ('不必重跑仿真'). This gives clear when-to-use context, but it doesn't explicitly mention alternative tools or exclusions, so it falls short of a 5.

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