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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=false, openWorldHint=true), so the description only needed to add non-obvious behavior. It does: a per-setup rate limit of 3 codes, a retry delay, and an irreversible recipient restriction ('never to any other number'). It does not say what the call returns or how a failure surfaces, which is the remaining gap.

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 dense sentences, front-loaded with the action and its recipient constraint before the follow-up instructions. Every clause carries operational information; nothing restates the tool name or schema.

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 two-parameter action with no output schema, the description supplies the practical loop (send → read code → confirm), the retry rule, and the invocation cap. Only the response behavior after sending is left unstated, a minor omission given the lightweight schema.

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 100% and both parameters (setup_id, status_token) are already documented with their origins and the privacy caveat. The description reinforces setup origin ('each setup gets 3 codes') but adds no syntax or failure-mode meaning beyond the schema. Baseline 3 applies.

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 ('Texts a 6-digit code to the mobile number') and immediately scopes it: the number comes from create_setup and 'never to any other number'. The single-destination constraint separates it from the generic sibling partner_send_code without the agent needing 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?

Gives explicit sequencing ('then call confirm_phone_code') and an explicit retry condition with an exclusion ('Call again only if it has not arrived after a minute'), plus the hard cap of 3 codes per setup. Both when-to-use and when-not-to-retry are stated.

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