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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered; the description goes beyond that by specifying exactly what is destroyed ('it and all its files'), that billing stops, that the action is irreversible, and that cleanup requires polling. That is meaningful added context, though it does not discuss failure modes or partial-state behavior.

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 tight sentences, front-loaded with the destructive action and its billing consequence, followed by the required pre-step and post-step. No filler and no repetition of the title.

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 single-parameter destructive tool with an output schema available, the description covers what it does, what it destroys, the reading prerequisite, and the follow-up polling. Nothing needed to invoke it correctly is missing.

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?

Only one parameter, and the schema already documents session_id at 100% coverage including the ses_… pattern and its origin (start_mac/list_mac_sessions). The description adds nothing about the parameter, so baseline 3 applies.

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 Mac session: shuts down the VM and permanently deletes it') plus the consequence (ends billing). An agent can distinguish it from read_mac_output, get_mac_session, and list_mac_sessions without opening any schema.

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 names the prerequisites and alternatives: read output first with read_mac_output, call whenever the task is done to avoid idle spend, then poll get_mac_session until cleanup_confirmed. When-to-use and sequencing are fully specified.

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