list_contacts

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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing deduplication by phone number, the sort order (saved first, then alphabetical), and the exclusion of non-dialable @lid identifiers. This tells the agent exactly what shape of data comes back and what is silently filtered out.

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?

Front-loaded with the core operation, then behavior, then a compact example block. Every sentence carries information and the formatting makes it scannable.

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 no output schema, the description carries the return-value burden and does so: dedup, ordering, and exclusion rules are all stated. An agent has everything needed to call it and interpret the result.

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 already 100%, so the baseline is 3, but the examples add real value by showing how is_my_contact, query, and limit/offset are combined in practice (e.g., {limit: 50, offset: 50} for page 2). It stops short of documenting edge behavior such as how limit/offset interact with the deduplication pass.

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 ('List WhatsApp contacts') and immediately scopes it to the local encrypted DBR3 cache with no network. This clearly separates it from get_contact (singular lookup), export_contacts (dump), and query (search tool) among siblings.

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 four worked examples cover the main invocation modes (unfiltered, saved-only, name search, pagination), which effectively communicates when to use each parameter combination. However, it never states when NOT to use this tool or points to an alternative such as get_contact for a single known contact.

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