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

Annotations only declare readOnlyHint=false; the description adds the important behavior that the call is confirm-gated and returns only a preview until confirm: true, and that validation happens at save time. It also discloses that no content is delivered until enrollment, which is material for a write tool. It stops short of describing error behavior or response shape.

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 fields, then validation and confirm behavior. Dense but every sentence carries useful information; the parenthetical confirm note is slightly awkward but not wasteful.

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 complex nested write tool with no output schema, the description covers the essential calling conventions: validation preconditions, confirm gating, and delivery semantics. Missing only secondary details like item count caps (300) and repeat scheduling, which the schema itself handles.

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?

With 50% schema coverage and a deeply nested payload, the description compensates by explaining the dayOffset convention (Day 1 = 0) and the per-item-type validation rules (message needs text, workout/nutrition needs a template, online session needs a link). That adds meaning beyond the schema, though it does not cover repeat rules or limits.

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 resource (create a program) plus the fields that define it (name, length in days, items). It does not distinguish this from closely named siblings such as create_plan, create_workout_plan, or create_weekly_message_series, leaving the agent to infer which constructor is appropriate.

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 line 'Nothing is sent to anyone until you enrol clients' implies the natural follow-up (enrollment) and clarifies the tool does not deliver content, which is useful context. However, there is no explicit when-to-use versus create_plan/update_program guidance, so the routing decision is only implied.

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