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

Annotations already declare read-only, non-destructive, open-world behavior, so the bar is lower; the description still reinforces 'Read-only'/'Does not publish' and adds genuinely new operational context: a cost of '1 credit' and the fact that output is constrained 'inside platform limits'. It does not cover error behavior or what happens when the brief is too long.

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?

Four clipped sentences, each carrying distinct information (output counts, competitor rule, no-publish boundary, cost), with the most important content front-loaded. The parenthetical character counts ('5 headlines (30)') are compact but slightly cryptic on first read.

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?

With no output schema, the description correctly takes on the job of describing the return shape (counts and platform limits per asset type), and it flags cost and side-effect status. Missing only minor detail such as language/tone handling or what happens if the brief is unusable.

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 80%, so most parameters are already documented; the description nonetheless adds semantics for the competitor parameter (name must never appear) and confirms the brief is the sole required input. Only 'brief' remains undescribed in either place, which is minor for a self-evident required 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?

Names a specific verb+resource (drafts ad variants) and quantifies exactly what is produced: 5 headlines, 2 descriptions, 1 Meta primary text, from a brief. It implicitly separates itself from the fetch-oriented siblings (competitor_ads_google/meta) by framing this as generation rather than retrieval, though it never names an alternative.

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 conditions for one input ('Pass competitor to make sure its name never appears') and a clear negative boundary ('Does not publish'), which implies you need a different tool to publish. It never names that alternative or states when to pick this over sibling drafting/export tools, so usage is only implied.

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