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

Goes well beyond the annotations: the 1 January 2027 objective expiry, the fact that a campaign alone does not spend, Smart+ campaign-level budget requirements, and the preview/confirm two-step behavior are all material behavioral facts not present in readOnlyHint/destructiveHint/idempotentHint. No contradiction with the declared non-read-only, non-idempotent profile.

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 core purpose and every sentence is substantive, but the expiry passage is verbose and repeats itself ('legacy manual flow', the reassurance about existing campaigns). Slightly dense but not padded with 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 complex 8-parameter creation tool with an output schema and annotations, the description covers the decision-critical constraints an agent needs (objective validity, budget mode/semantics, automation choice, confirmation flow). Nothing needed to invoke it correctly is missing.

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 schema description coverage at 0%, the description carries the whole burden and delivers: full enum lists for objective_type, budget_mode, automation and sales_destination, budget units ('50 = 50.00'), the confirm preview flow, and conditional applicability of sales_destination (Smart+ WEB_CONVERSIONS only). Only name and advertiser_id are left undocumented, both self-evident.

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 campaign') and implicitly distinguishes itself from sibling tools like create_meta_campaign and create_linkedin_campaign by platform, and from create_tiktok_adgroup by noting 'Delivery is enabled at the ad-group level'. An agent can identify its role without opening the schema.

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 explicit when-to-use and when-not-to-use guidance: four objective types have a hard expiry and 'will simply error and nothing is created', while TRAFFIC/REACH/VIDEO_VIEWS/ENGAGEMENT are unaffected. It also frames Smart+ as the replacement flow and states its exclusions (no PRODUCT_SALES).

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