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

Adds substantial behavior beyond annotations: it reads a local encrypted cache with no network, deduplicates by phone number across labels, defines sort order (saved before unsaved, then alphabetical), and excludes non-dialable @lid identifiers. These are concrete traits an agent could not infer from the readOnly/idempotent hints.

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-loads the key facts (source, dedup, sort, exclusion) before the examples, with no filler sentences. The examples section is slightly verbose but each maps to a distinct invocation pattern, so it largely earns its space.

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?

An output schema exists, so return values need not be explained. The description covers source, deduplication, ordering, exclusions, and pagination semantics, leaving no ambiguity for a correctly-formed call.

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 100%, so the baseline is 3; however the examples show how parameters combine (is_my_contact for filtering, query for search, limit/offset for pagination), adding practical meaning beyond the individual field descriptions.

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 and resource ("List WhatsApp contacts") plus scope (from the encrypted DBR3 cache, no network). Clearly distinguishes it from get_contact (single) and export_contacts (bulk export) 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 examples demonstrate invocation modes (all, saved-only, search, pagination) but never state when to choose this tool over alternatives like get_contact or export_contacts. Usage is implied through examples rather than explicit routing guidance.

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