save_structured_workout

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

With no annotations, the description carries the full burden and does well: it discloses the write/mutation, the token-binding requirement, the refusal cases, and that an overwrite backs up old steps to a file first. It leaves some gaps, such as permission/auth needs, what a token mismatch returns, and whether writes are idempotent, but the risky behaviors are surfaced.

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?

Four short sentences, front-loaded with the action and downstream effect, then preconditions, then refusal/overwrite rules. Dense with no filler, though the parenthetical about the nightly task slightly interrupts the flow.

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 6-parameter mutation with no annotations and no output schema, the description covers the guardrails and token workflow well but does not describe the return value, the meaning of workout_key, or the expected shape of steps. Adequate to call safely in the happy path, incomplete for error handling.

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 0%, so the description must compensate. It strongly explains preview_token (origin, binding to name and steps, approval requirement) and overwrite (needed to replace existing steps, triggers a backup), but leaves workout_key, date format, name, and the structure of steps entirely undocumented.

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?

States a specific verb and target system ('Write the previewed steps into the Final Surge Workout Builder') and adds the downstream effect ('Final Surge syncs them to the watch'). It is clearly distinguishable from the sibling preview_structured_workout, which produces the token this tool consumes.

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?

Gives explicit preconditions (preview_token must come from preview_structured_workout for exactly these name and steps, after athlete approval or inside the approved nightly task) and explicit exclusion conditions (refuses past dates, refuses a workout that already has steps unless overwrite=true). An agent knows both when to call it and when it will be rejected.

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