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

Annotations already declare idempotentHint=true, which the description reinforces. It adds value by explaining that re-running yields the same report and that sandbox campaigns get an illustrative sample report (marked sample: true), which is not in the annotations. This helps set expectations about output in different contexts.

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 concise at three sentences, front-loads the main purpose and output, and efficiently covers key behavioral nuances without fluff. Every sentence adds unique value, making it well-structured for quick parsing by an agent.

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?

Given the tool complexity (AI analysis) and available structured signals (output schema, annotations for idempotency), the description fully covers what an agent needs to know: main action, output, idempotency, and sandbox behavior. There is no ambiguity about input or output expectations.

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 input schema already has 100% coverage, with descriptions for both apiKey and campaignId. The description does not add additional parameter-level details, so it relies on the schema. Baseline 3 is appropriate because the schema adequately documents the parameters.

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 that this tool runs AI analysis over all answers and produces an executive summary with themes, sentiment, and quotes. It also differentiates itself from the related get_campaign_results by noting the report is also included there, helping an agent distinguish between generating the analysis and retrieving existing results.

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 explicitly notes when to run it (to generate a fresh analysis) and that re-running with no new answers returns the same report, implying idempotency. It also names get_campaign_results as a related tool where the report is available, guiding the agent on alternatives.

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