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

Annotations only flag destructiveHint=true; the description adds substantive preconditions (live subscribers block deletion) and the two-phase confirm-gated preview behavior, which the agent cannot infer from annotations. It stops short of stating irreversibility or whether subscribers/history are cascade-removed.

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 tight clauses with the destructive action, the blocking precondition, the alternative, and the confirm gate all front-loaded. Zero filler.

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 two-param destructive tool with no output schema, the description covers the key risks: blocking condition, safe alternative, and confirmation flow. Missing only permanence/cascade details and how to obtain planId.

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, the description compensates by naming the gating flag semantics ('previews until confirm: true'), reinforcing the schema-documented confirm parameter. planId is only implied as 'a coaching plan' identifier and its source/format is not described.

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 ('Delete a coaching plan') and adds a scope/blocking condition that distinguishes it from generic plan mutations in siblings like set_plan_active or update_plan_prices. It does not explicitly distinguish itself from delete_diet_plan/delete_workout_plan, so it stops short of 5.

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 an explicit when-not ('blocked while it has live subscribers') and names the alternative ('deactivate instead'), which maps to a real sibling behavior. It doesn't spell out what to do in other edge cases, but the primary decision path is clear.

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