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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so 'Read-only' in the description largely restates them. What the description does add beyond annotations is the fixed 30-day window, the data scoping keyed to the API key holder, and a concrete inventory of what comes back — genuinely useful behavioral context. It omits pagination, result caps, and empty-state behavior for what is clearly a multi-section payload.

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 sentences, both earning their place: the first front-loads the scope and enumerates the returned dimensions, the second closes off the main misuse case. No filler, no restatement of the name, and the most decision-relevant constraint (it's your own data only) is placed last for emphasis rather than buried.

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 parameters and no output schema, the description carries the burden of explaining the return payload, and it does so by naming each grouping and the creative list. Combined with annotations covering the safety profile, an agent has everything needed to decide to call it and interpret the result.

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?

The tool takes zero parameters, so there is nothing to disambiguate; the description correctly does not invent any input options. The implicit note that the window and scope are fixed (not configurable) is helpful because it tells an agent there is no date-range knob to look for.

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?

States a specific verb and resource ('Get this advertiser's own ad performance') and enumerates the exact breakdowns returned: by day, by app in the Spark network, by traffic source, plus owned creatives with review status. The phrase 'this advertiser's own' implicitly contrasts with the network-wide get_network_pulse sibling, so an agent can distinguish them without opening a schema.

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?

Clear context for use: last 30 days, scoped to the API key holder, and explicitly 'it cannot report on anyone else' — a useful exclusion that prevents misuse when an agent wants cross-advertiser data. It never names get_network_pulse as the alternative for network-wide data, so the when-to-use-vs-sibling routing is implied rather than stated.

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