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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so 'Reads only' is largely redundant. What the description adds beyond that is genuinely useful: it discloses what is returned in each branch (a card of demos vs. the exact next example call), which the annotations cannot convey. It stops short of describing the shape of that card or whether the demo call is executed or merely suggested.

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 sentences, front-loaded with the return behavior before the trigger phrases, so the agent reads the most decision-relevant fact first. Minor waste in 'Shows what Adonde can do', which echoes the title and the tool name.

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 one optional enum parameter, no output schema, and full annotation coverage, the description carries exactly the residual burden: trigger phrases, the alternative tools to route to, and the return shape for both param states. Nothing an agent needs to call 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?

Schema coverage is 100% and the enum is already listed, so the schema does the heavy lifting. The description still adds real meaning by stating the consequence of the parameter: omit it to get the demo menu, supply one to get the exact example call to run next — including the default behavior for an optional enum, which schemas rarely spell out.

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 and resource ('Shows what Adonde can do', 'runs a guided demo') and enumerates the two distinct return shapes by topic presence. An agent can distinguish this self-documentation tool from functional siblings like get_city_guide or get_menu 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?

Gives literal trigger phrases ('adonde help', 'adonde demo') plus the intent condition (asks what Adonde can do or how to use it), and explicitly excludes the real-work case by naming the alternatives: 'For a real trip, go straight to open_trip_form or start_trip.' When-to-use, when-not, and the replacement tools are all present.

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