preview_running_workout

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

With no annotations provided, the description carries full disclosure weight and exceeds the bar: 'no network call' declares the side-effect-free behavior, while validating single end condition per step, paired pace bounds, and pace format sets accurate expectations of what will be checked. The return contract (readable summary, sanity warnings, confirmation_token) is fully spelled out.

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 information-dense, front-loaded sentences deliver the core contract before a one-line token hand-off — almost no waste. The 'Args:' coda is slightly mechanical and adds little beyond what the schema title conveys, costing half a point.

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 tool with a deeply nested schema (steps, repeat groups, end conditions) and an output schema present, the description ties everything together: behavior (validate + no network), return package (summary, warnings, token), and workflow. The only unspoken edge is what happens when validation fails — whether the tool errors or returns an invalid-token sentinel.

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 'Args:' line is a thin restatement of the schema tree's intent, but the validation rules described (one end condition per step, paired pace bounds, pace format) do add genuine semantic meaning to how the workout parameter must be structured. Given 0% description coverage at the top level, however, the description under-serves the depth that a single high-level parameter with heavy nesting demands.

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 opening line, 'Assemble a running workout and show what WOULD be created — no network call,' uses a specific verb and object while immediately distinguishing the preview from an actual create operation. It clearly differentiates itself from sibling create_running_workout via the 'WOULD be created' framing.

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 instructs 'Always call this first and review the result,' giving an unambiguous directive on when to use it, and describes passing the returned confirmation_token to create_running_workout, naming the exact alternative workflow and sequencing.

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