train

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

With no annotations, the description carries the full burden. It reveals one key behavior: bridge automatically finds a friendly building capable of training the unit and issues the command. However, it does not cover failure cases, resource costs, or queueing behavior, leaving notable gaps.

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?

Two short sentences: the first states the action with examples, the second explains the bridge behavior. No filler, front-loaded, and every sentence earns its place.

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?

For a one-parameter tool, the description is mostly adequate for initial invocation, with examples and a behavioral note about building selection. Missing failure-mode handling, valid unit enumeration, and resource requirements leave moderate gaps, especially given no annotations and no output schema.

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 adds value by showing example values and implying unit_type is a unit identifier, but it does not enumerate allowed unit types or specify validation rules. This is only partial compensation.

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 uses a clear verb+resource pattern ('训练单位' = train unit) and provides concrete examples such as train("Terran_SCV") that make the operation unambiguous. It does not explicitly distinguish this from the sibling build tool, so it misses the top score.

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 intended use is implied by the description and examples—call this when you want a unit trained—but it never states when not to use it or names alternatives like build. Guidance is inferable rather than explicit.

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