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

destructiveHint=true already flags the destructive nature, and the description adds genuinely new context: what is preserved ('what they already received stays'), that the action is irreversible, and how to recover (re-enroll). The confirm-gating note duplicates the schema's confirm description rather than extending it, and nothing is said about required permissions.

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?

Three short clauses, front-loaded with the action and immediately followed by consequences and recoverability. The trailing parenthetical restates the confirm behavior already present in the schema, costing some space in an otherwise tight definition.

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 destructive mutation with no output schema, the description covers consequences, irreversibility, recovery, and the preview gate. The remaining gap is identifying what 'id' refers to and what the preview response contains, but the essentials for safe invocation are present.

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 50% — the confirm parameter is fully self-documented, but 'id' has no description anywhere. The description's 'for one client' nudges toward the id being a client identifier, yet it remains ambiguous whether it is a client id or a program-enrollment id, which is the single most consequential input for a destructive call.

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 ('Stop a program') scoped to 'one client', which is precise. It implicitly separates itself from pause/resume siblings via 'this cannot be undone', but never names pause_program_enrollment or resume_program_enrollment explicitly, so differentiation requires inference.

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?

It gives the restart path ('enrol them again to restart'), which points toward enroll_clients_in_program, and the irreversibility note hints that this is the terminal option versus pausing. However, there is no explicit 'use this instead of pause when...' guidance and no prerequisites or permissions stated.

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