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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is fully covered by structured data. The description adds nothing beyond that — no note on account-scoping requirements, no rate limits, no mention of which metrics or dimensions come back, and no hint that results are keyed by placement.

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 two sentences say the same thing twice: 'Meta results by placement (Feed, Stories, Reels…)' and 'Get performance breakdown by placement (Feed, Stories, Reels, etc.)' duplicate both the action and the identical placement list. Half the text could be deleted with no loss of information.

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 simple read-only breakdown query with no output schema, the description covers the basic purpose and annotations cover safety, which is roughly sufficient. However, it leaves the required date_preset unexplained and gives no indication of what the returned breakdown contains, which an agent would need to interpret results.

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 75% and the described parameters (adset_id, campaign_id, ad_account_id) are already self-explanatory there. The one real gap — the required date_preset enum, which has no schema description — is not compensated for in the description, and the interaction between campaign_id/adset_id filtering is never explained, so the description adds no meaning beyond the schema.

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 names a specific verb ('Get performance breakdown') and a specific resource ('by placement') for Meta ads, so an agent can tell it apart from the device and age/gender breakdown siblings by the resource dimension alone. It does not explicitly name those siblings, which keeps it at 4 rather than 5.

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?

The closing clause 'Use for placement optimization analysis' gives an implied use case, but there is no statement of when to prefer this over get_ad_performance_by_device, get_platform_daily_breakdown, or get_platform_performance, and no prerequisites or exclusions.

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