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

Annotations already establish readOnly, idempotent, and non-destructive behavior; the description adds genuinely useful behavior beyond that, such as default page size of 15, the 1000-record cap, scoping to the token's merchant or `merchant_id`, and the legacy-template caveat. No statement contradicts the annotations.

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 text is dense and front-loaded with the most decision-relevant information, and every sentence carries some useful content. It loses a point only for a slight redundancy where the pagination/count behavior is described in both the first paragraph ('returns 15 at a time') and the second ('Capped at 1000 records per page').

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?

Given the rich input schema, output schema, and strong annotations, the description covers the remaining needed context: how to pick the correct template, what legacy types mean, how pagination works, and how merchant scoping applies. An agent can safely and correctly call this tool without additional documentation.

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, but the description materially enriches the `type` parameter by mapping each enum value to a concrete interview modality. It also gives practical meaning to `offset`, `filter_text`, and `merchant_id` through pagination and scoping guidance, which goes beyond the schema without restating every field.

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 names a specific operation ('List available avatar/voice templates') and a specific resource, then explains what returned items mean. It clearly distinguishes itself from sibling tools by defining how `type` maps to interview modality, so an agent knows this is for template selection, not for listing interviews or candidates.

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?

It explicitly tells the agent to choose the template whose `type` matches the intended experience and that the returned `id` becomes `interview_template_id` for create-interview tools. It also provides concrete operating guidance: paginate with `offset` while `pagination.has_more` is true, narrow with `type`/`filter_text`, and avoid legacy `offline_elai`/`offline_synthesia` types for new interviews.

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