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

Annotations already cover the safety profile (readOnlyHint true, destructiveHint false, openWorldHint false), and the description adds real value beyond them: it saves no company data, it is safe to repeat, it requires an authenticated Corply connection, and it returns a signed structured selection. The generic 'confirmation boundary' boilerplate listing unrelated categories (reversible save, plan refresh, standing policy) is noise and slightly muddies the picture, keeping this from a 5.

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?

Purpose and key facts are front-loaded, which is good, but the description is padded with a long generic 'confirmation boundary' sentence enumerating unrelated action categories that do not apply to an address picker. Those words do not earn their place.

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 tool with no output schema and an undocumented nested parameter object, the description adequately explains the flow (opens UI, returns signed selection, saves nothing) but leaves parameter usage and sibling differentiation unaddressed. It is workable but has clear gaps.

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% across three parameters, including a nested _corply_context object, so the description carries the full burden — and it provides nothing about what 'input', 'label', or the context id/receipt mean or how to format them. The only hint is the vague phrase 'for a new or changed address'.

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?

The description states a specific action and artifact: 'Open Corply's Google-powered autocomplete UI for a new or changed address,' and clarifies it returns a signed structured selection rather than saving data. That is clear, but it never distinguishes this picker from the closely-named siblings suggest_addresses and resolve_address, so an agent still has to guess between three address tools.

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?

'For a new or changed address' implies the usage context, and it notes the selection should be reviewed before being used in a company tool. However, no alternative is named — suggest_addresses and resolve_address occupy the same conceptual space and the description gives no condition for choosing among them.

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