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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds behavioral context beyond those, including the computational method (Minetti gradient cost) and the returned metrics (pace, elevation gain/loss, average grade), which helps the agent understand what happens.

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 two concise sentences, front-loaded with the primary action and followed by output details and a source reference. No wasted words.

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?

With an output schema present, the description does not need to explain return values. It covers the purpose, method, split units, and source, making it complete for tool selection and invocation in the context of a course profile and goal time.

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 provides 100% description coverage for all three parameters. The description does not add syntax or format details beyond what the schema already offers, but it does tie the parameters together (goal time, profile, split unit) in the overall purpose. 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 function: distribute a goal time across a course profile using Minetti gradient cost. It specifies the action, resource, and output (per-mile or per-km splits with pace, elevation, and grade), and distinguishes it from siblings like pacing_strategy and predict_race_time.

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 implies usage context: when a goal time and course profile are available, use this to compute splits. It does not explicitly mention when not to use it or compare to alternatives, but the specific nature of the tool makes the context clear enough for an agent.

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