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

Annotations already declare write/destructive/non-idempotent/open-world, so the safety profile is covered; the description adds genuinely non-obvious behavior: per-call and per-list caps, that duplicates and invalid numbers are silently counted rather than rejected, and that no calls are placed. It does not explain why destructiveHint is set or what partial-failure looks like, which keeps it below 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?

Three tight sentences, front-loaded with the write action and scope, then limits, then edge-case semantics. Every clause carries information an agent cannot get from the schema or annotations; there is no restatement of the title.

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 3-parameter bulk mutation with no output schema, the description covers input shape, limits, and failure semantics well. It stops short of saying what the response contains (presumably counts of added vs. skipped), which an agent would want given the emphasis on counting duplicates.

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 0%, so the description must carry the load and does: it specifies the shape of each `people` entry ({phone, name, vars: {column: value}}), the bare-phone-number shorthand, and the leading-single-0 calling-code rule. It also clarifies that the list can be addressed by either integer id or uuid. The only gap is precedence when both identifiers are supplied.

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 ('Adds') and resource ('people to a saved list'), and immediately names the two identifying parameters (voip_list_id / voip_list_uuid). The VOIP qualifier plus the '[write]' tag makes it trivially distinguishable from add_sms_list_members, add_email_list_members, and from add_voip_optouts.

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?

Usage context is implied through operational details (the 500/2000 caps, duplicate handling, and the note that the do-not-call list is only enforced at campaign-add time), which tells an agent when this tool is safe to bulk-load. However, it never explicitly states when to choose this over add_voip_optouts or import_voip_campaign_targets, and gives no prerequisites for the list existing.

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