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

Annotations only declare readOnlyHint=false, so the description carries the real load: it discloses the preview/execute gate, idempotent no-op behavior for duplicates, and a 200-member ceiling. It does not say whether exceeding 200 errors or partially applies, nor what the preview contains, keeping it at 4 rather than 5.

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?

One compact sentence with parenthetical qualifiers; the core action is front-loaded and every clause (ownership, idempotency, cap, confirm gate) carries information an agent needs.

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 3-param mutation with no output schema and only a readOnly annotation, it covers the critical operational facts: ownership restriction, idempotency, size limit, and the confirmation flow. Missed only the failure/partial-success semantics and preview return shape.

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 33% — groupId and clientIds have no schema descriptions — so the description must compensate. It clarifies that clientIds are the coach's own clients and that the array is capped at 200 per group, but adds nothing about groupId format or the limits on each ID.

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?

Names a specific verb and resource ("Add clients to a group") and immediately scopes it to "the coach's own clients only." That distinguishes it from group-agnostic membership tools like add_member_to_gym_class_session, though no sibling is named explicitly.

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 clear qualifying conditions: only the coach's own clients, up to 200 per group, and it is safe to re-add existing members. The confirm-gate is also flagged. It stops short of naming an alternative tool or saying when to use remove_group_members instead.

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