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

Annotations mark it as non-destructive but open-world. The description adds critical context beyond that: all objects are created disabled, spend requires a separate activation call, dailyBudget is in whole currency units with a 20 USD minimum, and startDate must be after today in the account's timezone. It also documents the idempotency retry contract.

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 disciplined: it front-loads the action and disabled-state fact, then layers constraints and dependencies. Every sentence carries operational value with no filler.

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 13-parameter, nested-object, no-output-schema tool, this is close to complete: it covers safety, sequencing, value constraints, and data dependencies. Minor gaps remain around goal semantics and how the created ids surface (implied via campaignRecordId mention), so not a full 5.

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 description coverage is only 31% across 13 parameters, so the description compensates well: it clarifies dailyBudget units/minimum, startDate timezone constraint, locationIds sourcing, and the identity two-path (existing id vs displayName+avatar). It doesn't cover goal enum meaning or every nested creative/targeting field, leaving some gaps.

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 opens with a specific verb and resource set: 'Create a TikTok campaign, ad group and video ad... from a video URL or staged upload.' This clearly distinguishes it from sibling tools like ads_create_campaign and ads_create_account by specifying the full three-object hierarchy it creates.

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?

Explicitly states 'Nothing spends until ads_set_status activates the ad,' pointing to the required follow-up sibling. It also routes to ads_list_targeting for location ids and ads_list_identities for identities, and explains the retry behavior with idempotencyKey. This is thorough when/where guidance plus alternatives.

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