smartgym_create_program

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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, but the description adds substantial context beyond them: all-or-nothing validation, the dry-run-first safety workflow, deterministic fuzzy matching of exercise names, and the flagged default set when sets are omitted. This is exactly the kind of behavioral disclosure that reduces accidental destructive calls.

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?

Front-loaded with the core action and outcome, then proceeds into parameter detail in a logical order. It is dense and somewhat long, but nearly every clause carries payload (validation mode, day encoding, default-set flagging) rather than filler. Minor tightening could still help, so not a full 5.

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 need not document return values, and it correctly focuses on inputs and behavior. For a nested, multi-routine mutation tool with rich annotations, it covers validation, dry-run semantics, name-uniqueness, and section ordering fully — nothing an agent needs to call it correctly is missing.

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?

Top-level schema coverage is effectively 0% (dry_run and routines carry no inline descriptions), so the description must carry the burden and does: it explains dry_run semantics, the routines structure, required name uniqueness, the optional days/goal/note fields, and the weekday numbering scheme (1=Sunday…7=Saturday). It adds real semantic meaning for nested specs (exercise fuzzy-match, rest_seconds, sets defaults) beyond what the schema offers.

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+resource ('Create one or more routines (a program) on the SmartGym server') and immediately distinguishes scope ('all devices get them'), which separates it cleanly from update_routine, add_exercise, and the other routine-mutating siblings. An agent can identify the create-vs-update boundary without opening any schema.

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 gives strong operational guidance: dry_run=true is the default and 'sends NOTHING', while dry_run=false actually creates and verifies on the server, and validation is all-or-nothing. It stops short of naming sibling alternatives (e.g. when to use update_routine instead), so it is clear context without explicit exclusions.

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