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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds value by disclosing what data the preview surfaces (targeting, event, bid, budget, page, Instagram, texts, URL, CTA), but it remains silent on what happens if both ad_id and adset_id are supplied, or if neither is.

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 opening sentence front-loads the purpose well, but the second sentence largely restates it ('settings a launch would copy' vs 'settings that would be copied') while appending the field list. It is not bloated, but the redundancy means one of the two sentences does not fully earn its place.

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 read-only preview tool with no output schema, enumerating the copied fields is genuinely useful and partially compensates for the missing return-value documentation. However, with two optional parameters whose combination semantics are undefined, the definition should state the minimum required input and whether ad-level and ad-set-level previews can be requested together.

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 100% and each parameter points to its companion listing tool ('An ad (list_ads)', 'An ad set (list_adsets)'), so the schema carries the parameter burden. The description adds no format, cardinality, or combination rules beyond that baseline.

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 gives a specific verb ('Preview') plus the precise resource: the settings a launch would copy from a Meta ad set or ad, and it enumerates the concrete fields involved (targeting, event, bid, budget; page, Instagram, texts, URL, CTA). The only gap is that the name 'get_templates' suggests a template listing, and the description never contrasts this with the sibling list_platform_templates, so an agent must infer the difference.

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?

Usage is only implied by the phrase 'a launch would copy' — there is no explicit statement of when to call this versus list_platform_templates, get_launch_questions, or the plain list_ads/list_adsets tools. It also does not say that at least one of ad_id or adset_id must be supplied, which matters because the schema declares zero required parameters.

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