Create Hevy Routine

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

Annotations declare readOnlyHint=false, which alone would imply every call mutates; the description usefully corrects that by explaining the default is a non-writing preview. It still says nothing about auth requirements, duplicate-title handling, or what the preview returns relative to the write, so it stops short of full disclosure.

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 sentences, zero waste, with the mode distinction and the write-safety rule front-loaded. Nothing here would be better removed.

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?

An output schema exists, so return values need no explanation, and the write-gating rule is covered. For a tool whose only parameter is a large nested object with no field documentation, however, the definition leaves an agent without the information needed to build a valid routine payload.

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 0% and the schema contains a deeply nested routine object (title, notes, folder_id, exercises with exercise_template_id, sets, reps, weight_kg, rest_seconds, superset_id, rep_range). The description only explains dry_run, leaving the entire required routine payload—including how to source exercise_template_id—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?

The description states a specific verb and resource ('Preview or create a Hevy routine') and makes the two modes explicit. It does not differentiate the tool from siblings such as update_hevy_routine or create_hevy_workout, but the create-vs-preview split is unambiguous.

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?

'Set dry_run=false to write to Hevy' plus 'Only execute a write when the user has requested it' gives a clear condition for the mutating path and an explicit exclusion. It offers nothing on when to prefer create_hevy_routine over update_hevy_routine, or what prerequisites (e.g. a valid exercise_template_id) must be gathered first.

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