Fetch the phone's address book again

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

The description provides several behavioral details beyond the annotations: it waits up to 15 seconds, it changes nothing on WhatsApp, and it refills wazap's own contact list. It also explains the expected return values and how to interpret them. The emphasis that 'only refills wazap's own contact list' reconciles the idempotent and read-only hints rather than contradicting them.

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 description is compact yet complete. It opens with the main action, then adds the critical caveat that WhatsApp is unchanged, followed by usage conditions and return-value guidance. There is no filler and every sentence contributes to helping an agent invoke the tool correctly.

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?

The tool has no output schema, so the description appropriately explains exactly what the return values (named_before and named_after) mean, including how to interpret when both are 0. It also covers idle timeout, side effects, and trigger conditions. For a zero-parameter refresh action, this is complete.

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?

The tool has zero parameters, so there is nothing for the description to explain about input meaning. The schema coverage is already 100% and there are no parameter fields. The description focuses instead on behavior and outputs, which is appropriate. Given no parameters, the score is set to the baseline of 4.

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 clearly states the specific verb and resource: it refetches the linked phone's address book for wazap's own contact list. It distinguishes this from simple lookups like get_contact or search_contacts by emphasizing the 'from scratch' refill action and the absence of any change on WhatsApp. The title and description work together to make the tool's intent unambiguous.

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?

The description explicitly tells when to use this tool: when get_status reports contacts_named is 0, or when group senders show as phone numbers instead of saved contact names. It also explains how to evaluate the outcome via named_before and named_after. This gives an agent concrete criteria for selecting it over other tools.

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