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

Annotations declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=false), and the description adds the crucial effects annotations cannot convey: no write reaches Google, Instagram, or any customer, and every result is labeled DEMO. It also discloses the fresh:true reset scope and the switching 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?

Front-loads the eligibility rule, then the effect, then the safety guarantee, then the switching/exit mechanics. Dense but every clause is load-bearing; the only slight overhead is the long enumeration of business types.

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 stateful mode-switching tool with no output schema, it covers eligibility, side effects, isolation guarantees, reset behavior, switching, and the exit tool. An agent has everything needed to invoke it correctly and to know what will not happen.

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%: fresh is documented in the schema and the description reinforces what it resets ('profile, drafts, history, appointments'). account_type has only an enum in the schema with no description, but the description enumerates the demo business types, adding real meaning beyond the raw enum values.

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 action (switch Claude into demo mode as a made-up business) with the resource and scope (agency/admin accounts only). It is immediately distinguishable from the sibling stop_demo, which it names as the exit path.

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?

Explicit preconditions ('For AGENCY accounts (and ShearQuery admins)'), explicit mode-switching guidance ('Call it again with another type to switch'), explicit reset semantics, and an explicit alternative ('Call stop_demo to leave'). Nothing is left to inference.

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