train_status

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

No annotations provided, so description carries full burden. Describes what data is returned: step/total, loss, recent samples, log tail, result paths when done. Implies read-only operation; no side effects mentioned but none expected. Could explicitly state it is non-destructive.

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 sentences, no fluff. First sentence covers both usage modes. Efficiently packed with information.

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 simple one-parameter tool, description covers key behaviors: single-job details and listing all jobs. No output schema exists, so description compensates with field details. Could mention list format (e.g., just IDs or summaries), but 'newest-first' gives ordering. Adequate for the complexity.

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 100% with parameter description, but description adds significant value: explains that id comes from train_start, specifies the two usage modes, and lists the output fields. This enriches the parameter meaning beyond the schema alone.

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?

Description clearly states 'Check training progress' (verb + resource) and differentiates two modes: with a specific job ID (returns detailed progress fields) or without (lists all jobs newest-first). This distinguishes it from siblings like train_start, train_cancel, get_job_status.

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?

Explicitly tells when to use with id ('pass an id for one job') and when to omit ('omit for all jobs'). Does not mention alternatives or when not to use, but the behavior is clear from context.

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