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

Annotations already declare readOnly/openWorld/non-destructive, and the description adds substantial context beyond them: no persistence, idempotent/safe to repeat, no company required, provisional Google-sourced data, and that no Corply fact is read or changed. The confirmation-boundary statement further clarifies no extra confirmation is required.

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?

The first sentences are front-loaded and efficient, but the trailing 'Confirmation boundary' sentence is a long boilerplate list covering many unrelated case types (fact/evidence record, link preparation, plan refresh, standing policy) that dilutes the entry and adds little value for this specific tool.

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 simple suggestion tool with no output schema, the description covers the workflow, safety profile, and idempotency well, and implies a placeId return via the resolve_address reference. It leaves the nested _corply_context parameter and the shape of returned matches undocumented.

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 description coverage is 0%. The description conveys that 'input' is new address text, but gives no length/format guidance, and the nested _corply_context object (id/receipt) is entirely unexplained. With two parameters and zero schema documentation, the description does not compensate for the coverage gap.

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 (find/suggest), resource (addresses), and scope ('up to five Google matches for new address text'). It distinguishes itself from resolve_address by naming it as the follow-up consumer of the returned placeId, so an agent can tell them apart without opening schemas.

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?

Makes the workflow explicit: this tool only suggests, the selected placeId must then go to resolve_address, and 'this tool saves nothing.' That clearly frames the context of use. It stops short of an explicit when-not to use it or a named alternative for other address entry paths (e.g. show_address_picker).

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