train_doctor

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

No annotations are provided, so the description carries the full burden. It explicitly states '只查不装' (read-only, no installation), which discloses the non-destructive nature. It also indicates the tool performs anti-cheating checks (git disabled, .git visibility, network whitelist) that might involve probing. This is good transparency for a diagnostic tool, though it doesn't mention permissions or side effects in detail.

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 but well-structured with dashes and semicolons. It front-loads the purpose and includes behavioral notes. It is concise given the amount of information conveyed, though it could be broken into clearer sections.

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 diagnostic tool with two parameters and no output schema, the description is fairly complete. It lists what it checks, states it's read-only, and gives installation alternatives. It doesn't mention the return format, but that's not critical. It covers the main aspects an agent needs to call it 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?

Schema description coverage is 100%, so the schema already documents both parameters with detailed descriptions (enterprise_id as required, dataset_mount_path as optional with purpose). The tool description does not add any additional parameter semantics beyond what the schema provides. Baseline 3 is appropriate.

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 purpose as a training environment health check (训练环境体检) and enumerates the specific checks: CUDA, memory, framework version, base model cache, plus three anti-cheating baselines. This is specific and distinguishes it from generic tools. However, it does not explicitly differentiate from sibling tools like train_diagnose or train_status, so it doesn't fully clarify when this one is preferred over those.

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 provides explicit guidance: '只查不装' (only check, don't install) and redirects installation to a specific script (bash tools/train/train-env-init.sh). It also explains the base model handling. This is clear usage guidance, though it doesn't mention alternative MCP tools, so it could be stronger on when to use this vs. train_status or train_diagnose.

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