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

Annotations already declare readOnlyHint, idempotentHint and non-destructive behavior, so the safety profile is covered. The description adds only that the breakdown yields three device buckets; it says nothing about date-range requirements, result granularity (account vs campaign vs adset), or aggregation behavior.

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?

Two short sentences, front-loaded with the verb and dimension. The opening fragment "Meta results by device" largely restates the following sentence, a minor redundancy, but nothing bloats the definition.

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 reporting tool with annotation coverage and a mostly documented 4-parameter schema, the essentials are present. Gaps remain around result shape and how optional campaign/adset scoping changes the output, which matter for a metrics tool with no output schema.

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 75%, with ad_account_id explicitly sourced to list_ad_accounts and the enum for date_preset self-documenting. The description contributes no parameter meaning of its own — notably it never explains that campaign_id/adset_id narrow the breakdown scope, which is the main thing an agent would need clarified.

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?

"Get performance breakdown by device (mobile, desktop, tablet)" names a specific verb and resource dimension, and the enumerated device values make the scope concrete. It does not explicitly differentiate itself from lookalike siblings such as get_ad_performance_by_age_gender or get_ad_performance_by_placement, though the dimension is self-evident.

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?

"Use for device optimization analysis" gives a use-case hint but no explicit when-not conditions, no prerequisites (e.g. you need an ad_account_id from list_ad_accounts), and no routing guidance toward sibling breakdown tools. Usage is implied rather than instructed.

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