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

The description leads with 'Read' and explicitly disclaims mutation ('Does not create ads or change budgets'), i.e. it presents this as a read-only operation, while the annotations declare readOnlyHint=false. This is a direct inconsistency between the description's stated behavior and the structured safety hint. The useful detail that currencies, reporting periods, freshness, and missing metrics are preserved cannot offset a contradictory safety signal.

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?

Three short sentences, front-loaded with the core purpose and free of filler; the caveat sentence earns its place as a scope clarifier. Structure is strong, though the terseness is partly to blame for the parameter and sibling gaps.

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?

An output schema exists, so return-value structure need not be described. But with 7 parameters at 0% schema coverage and several near-identical siblings, the description leaves real gaps in parameter meaning and tool selection, making it only minimally complete.

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 0% across 7 parameters, so the description must carry the burden. It does clarify the provider enum values (Meta, Google Ads, Pinterest) and hints at the since/until semantics via 'completed dates', but brandId, accountId, connectionId, and the 'fresh' flag are entirely unexplained.

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 (Read) and resource (advertising performance across Meta, Google Ads, or Pinterest), plus a scope qualifier (completed dates). It is clear on its own, but it does not differentiate itself from close siblings like get_ad_breakdown, get_ad_campaign, or get_performance_report, which also read ad performance data.

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 phrase 'for completed dates' implies a usage boundary (not for in-flight/future dates), and 'Does not create ads or change budgets' tells the agent this is not a mutation path. However, it names no alternative for the overlapping ad-performance siblings, so selection still requires inference.

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