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

The annotations provide readOnlyHint=true, so the read-only behavior is already declared. The description adds valuable context: the data is over a 'configured window', filters are passed as query params, and the operation is scoped to the active Space. This goes beyond annotations by explaining the scoping mechanism and the nature of the returned aggregates.

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 description is three sentences, each serving a distinct purpose: stating the return value, explaining filter usage, and clarifying Space scoping. There is no redundant text or filler. It is compact, front-loaded with the core action, and every sentence adds value.

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?

The tool has no output schema, so the description partially covers the return fields by listing impressions, clicks, conversions, and spend. It also provides the endpoint reference for more details. It doesn't specify the response structure (e.g., array vs object), but given the readOnly annotation and the mention of the spec, it is reasonably complete for an agent to invoke correctly. A minor gap is the meaning of 'configured window', which is left unexplained.

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 schema defines space_id with a clear description and allows additional properties, but doesn't explain that additionalProperties correspond to query-param filters. The description explicitly states to pass query-param filters as keyword arguments and references the OpenAPI spec for the full set. This significantly enriches the parameter semantics beyond the schema alone.

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 clearly states the tool returns aggregated performance stats (impressions, clicks, conversions, spend) over a configured window. This specific verb+resource+scope distinguishes it from sibling getters like get_ad or get_campaign, which fetch individual entities. The mention of 'aggregated' and 'performance stats' makes the purpose unambiguous.

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 description explains how to use query-param filters via keyword arguments and points to the OpenAPI spec for the full filter set. It also clarifies the Space scoping and how to override it with space_id or by using set_active_space. While it doesn't explicitly name alternative tools to use instead, the context is clear that this is the tool for aggregated stats and not for single-object data.

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