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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real interpretive behavior beyond that: report results as evidence not proof, and disclose provisional readouts, which shapes how the agent should present the data.

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?

Front-loaded with the core purpose, then capabilities, usage trigger, return shape, and caveats in scannable paragraphs. The inline return block is justified by the absence of an output schema; only minor redundancy between "decision readout" and the Returns list keeps it from a 5.

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 output schema, the description usefully sketches the return shape and adds interpretation guardrails, which covers most of what an agent needs. The unexplained parameters and no sibling differentiation leave a small gap.

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%, so the description carries full responsibility for the three parameters (runId, ideaId, response_format). It never mentions or explains any of them, nor the meaning of runId vs ideaId, leaving the semantic burden unmet.

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 (get) and resource (decision readout for one Ad Run) and enumerates the payload: validation score and band, confidence, signals, and recommended next move. This lets an agent distinguish it from siblings like idealaunch_get_ad_run or idealaunch_get_run_events without opening any 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?

"Use it when the user asks how a test went, or what they should do next" gives clear triggering context, and "flagship result tool" signals priority. It stops short of naming alternatives or when-not-to-use conditions versus the sibling run/event tools, so it does not reach a 5.

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