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

Annotations declare idempotentHint=true and destructiveHint=false, and the description adds genuinely useful context beyond them: the demo business and any changes made within it are preserved 'for next time'. That persistence detail is the kind of non-obvious consequence an agent needs and is not covered by the annotations.

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 sentences, action front-loaded ('Leave demo mode.'), with each following sentence earning its place by explaining the scope and state effects. No 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?

With no parameters, no output schema, and annotations covering the safety profile, the description is nearly sufficient; it explains both the scope switch and data retention. It could optionally note behavior when not in demo mode, but nothing essential 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?

The tool takes zero parameters, so there is no parameter semantics to convey; the 4 baseline for a 0-param tool applies. Nothing is misrepresented.

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 ('Leave demo mode') and immediately clarifies the resulting behavior: business tools return to answering about the account's own business. It is cleanly distinguishable from the inverse sibling start_demo without opening either 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?

Usage is implied by the state transition ('Business tools go back to answering about this account's own business'), so the agent can infer when it applies. However, no explicit when/when-not guidance or named alternative (start_demo) is provided.

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