train_list

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

With no annotations, the description carries the full behavioral burden. It does disclose the sources it enumerates (live or recent containers plus checkpoint log directories), which tells the agent this is a broad discovery call rather than a filtered one, but it says nothing about read-only safety, staleness/recency semantics of 'recent', or whether it touches remote hosts.

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 single front-loaded sentence with the verb and resource first, followed by a compact colon-style enumeration of what is listed. No filler, no restatement of the title.

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?

An output schema exists, so return-value explanation is unnecessary, and with zero parameters the schema side is fully covered. The description is adequate for a simple enumeration tool, though it leaves the boundary against train_status and train_checkpoints undefined.

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 tool takes zero parameters, so there is nothing for the description to clarify; baseline 4 applies. The description correctly avoids inventing filter semantics that do not exist in the 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?

States a specific verb ('List') and resource ('training runs') and adds scope detail about what a run comprises (live/recent containers, log directories holding checkpoints). It is clear on its own, but it does not differentiate itself from siblings like train_status or train_checkpoints, and the mention of 'log directories holding checkpoints' partially overlaps with train_checkpoints.

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?

There is no when-to-use guidance, no exclusions, and no named alternative. An agent must infer whether to call train_list vs train_status vs train_checkpoints, especially given the checkpoint overlap. Nothing tells the agent under what conditions this is the right call.

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