get_whats_working

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

With no annotations, the description carries the full burden, and it partly meets it by disclosing the shape of the result set (ranked channels, growth, conversion rate, recurring spike causes). It does not state that this is a read-only aggregation, whether results are cached or rate-limited, or how "recurring" spikes are determined — meaningful gaps on an unannotated tool.

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, no filler, and the high-value content (what the tool returns) is front-loaded before the invocation advice. Every clause earns its place.

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?

There is no output schema, so the description usefully enumerates the returned evidence categories, which is the main thing an agent needs to trust the result. It is nearly complete for a single-optional-parameter tool; only the read-only/mutation status and any result limits go unstated.

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 100% and the single `range` parameter is fully documented in the schema with format examples and a default. The description adds nothing about the lookback window, so the baseline 3 applies.

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 concrete composite resource — channels ranked by conversions with growth and conversion rate, growing pages, and recurring spike causes — so an agent knows exactly what comes back. It stops short of distinguishing itself from overlapping siblings (top_sources, top_pages, find_traffic_spikes, explain_spike), leaving the agent to guess whether this is a superset or a different cut of the same 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?

"Use this before proposing marketing ideas" gives one clear situation for invoking the tool, which is real guidance. It offers no when-not condition and never names the sibling tools (top_sources, top_pages) that partially overlap, so the agent must infer whether to call this instead of, or in addition to, them.

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