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

Annotations only define safety flags (readOnly=false, destructive=false, idempotent=false); the description adds meaningful context beyond them — server-side SHA-256 hashing so raw PII never leaves, the ~1000-user match threshold, and the confirm=false preview vs confirm=true apply distinction. It does not address what happens on repeated calls (idempotency), leaving one gap.

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?

Dense but tightly organized, leading with purpose before dropping into identifier format, hashing, threshold, and confirm behavior. Every clause carries information; the parenthetical aside is the only slight fold-in of optional framing.

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 5-param mutation tool with an output schema, the description covers the non-obvious parameters, the data-handling behavior, and the preview/apply switch. Only the mundane name/advertiser_id params and idempotency behavior are unaddressed, which is a minor shortfall.

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?

With 0% schema description coverage, the description carries the burden and largely does: it defines identifiers as comma- or newline-separated emails/phone numbers, enumerates id_type values (EMAIL | PHONE), and explains confirm's preview/apply semantics. name and advertiser_id remain unexplained, keeping it below a 5.

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 ('Creates a TikTok custom audience from a CUSTOMER LIST') and immediately distinguishes it from the sibling create_tiktok_lookalike_audience by framing the customer list as a lookalike seed rather than a lookalike itself.

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?

Gives clear context for when to reach for it (retargeting CRM contacts, seeding a lookalike) and a concrete viability threshold (roughly 1000+ matching users). It does not explicitly name a competing audience-creation tool for when this is the wrong choice, so it stops short of a 5.

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