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

Annotations already mark this non-read-only and destructive, so the description's job is to add context, and it does extensively: partial-update semantics ('omitted fields keep their current values'), full-replacement behavior for exercises, preservation of progression links for exercises that keep their name, and the identity-only role of workout_folder_name (never a move). No contradiction with annotations — idempotentHint is consistent with the full-array replacement semantics, since re-sending the same complete array yields the same state.

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?

Long, but every sentence carries load for a genuinely complex tool with nested exercise arrays, supersets, rest modes, and two distinct update paths (rename vs. full replace). The approval gate is front-loaded, and the labeled name:/exercises: list makes the two modes scannable. The density of parentheticals costs it the last point, not the overall length.

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?

Given an output schema, 100% schema parameter coverage, and annotations, the description covers every operational decision: when the call is permitted (after explicit approval), how to identify the target (exact current name, folder only for disambiguation), what to omit (unchanged fields), what to read first (get_workout_detail), and when no read is needed (rename-only). Routing to server instructions for the shared approval workflow is acceptable delegation rather than a gap.

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 100%, so the baseline is 3; the description earns a 4 by adding cross-parameter semantics the schema cannot express: 'provide only what changes; omitted fields keep their current values' governs how to treat every parameter, and the rename shortcut ('pass workout_name and name only') is stated in the description. The exercises paragraph reinforces the schema's read-modify-write loop rather than duplicating field-level formats.

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?

Opens with 'Update an existing workout template' — a specific verb and resource — and immediately differentiates from siblings: partial updates versus create_workout's creation, the get_workout_detail read-first prerequisite versus direct reads, and the explicit note that this tool never moves workouts between folders. There is no ambiguity about what operation this performs or which sibling it is not.

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 gates invocation: 'Only call this after the user has reviewed the proposed change and approved it,' and routes the agent to create_workout's approval workflow. It states the prerequisite read ('First call get_workout_detail and edit the object it returns') and the exclusion case ('A rename needs no prior read: pass workout_name and name only'), plus the exact condition for adding workout_folder_name. An agent can decide precisely when this tool rather than a sibling is the right call.

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