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

Annotations already declare readOnlyHint: true and destructiveHint: false. The description adds valuable behavioral context beyond these, such as token download duration (30 days for public, no limit for private), inclusion of benchmark results and download URLs when completed, and the ladder job candidate structure. It does not contradict the annotations, and the extra transparency aids agent decision-making.

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 paragraph, but every clause provides actionable information—state transitions, polling cadence, output specifics, and ladder job details. There is no filler, though splitting into shorter sentences could improve readability. It is front-loaded with the core status flow, making it efficient.

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?

Despite no output schema and only two parameters, the description covers all critical aspects: state transitions, polling frequency, post-completion content (benchmark results, download URLs), public/private differences, and ladder job handling. It provides enough context for an agent to interpret responses and take appropriate actions without needing additional documentation.

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 50% (only 'engine' has a description; 'job_token' has none). The tool description does not explain what job_token is or that it comes from create_training_job, nor does it clarify any parameter relationship. Since the description fails to compensate for the incomplete schema, parameter semantics are insufficient.

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 explicitly states the tool's purpose as checking job status, outlining the state flow (awaiting_payment -> paid -> submitted -> completed (or failed/expired)). This clearly distinguishes it from sibling tools like create_training_job and pay_training_job, with a specific verb+resource (get + training job) and actionable scope.

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?

Provides explicit when-to-use instructions: 'Poll every 60-120s after paying.' It also details what to do with results, including download URL handling for public vs private jobs and ladder job selection (take the winner, compare using specific metrics). This goes beyond mere context and gives actionable guidance, though it does not name alternative tools explicitly.

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