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

The description adds valuable behavioral context beyond annotations: privacy thresholds (5 answers for open link, minPercent for targeted), the inclusion of a count and remaining need, anonymity by construction, conditional AI report inclusion, and a 30-day data deletion policy. This significantly helps the agent understand the tool's behavior without contradicting the readOnlyHint and idempotentHint annotations.

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 a single, information-dense sentence that efficiently conveys all key points. It is front-loaded with the primary output ('The answers') and then adds essential details without redundancy. Though it is a long sentence, it remains readable and well-structured.

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's complexity and the presence of an output schema, the description covers the critical contextual aspects: availability conditions, content of the response, anonymity, conditional AI report, and data retention. It does not detail error cases or exact output field names, but these are not required given the output schema exists.

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 coverage is 100% with detailed descriptions for both apiKey and campaignId. The tool description does not add any additional meaning to these parameters, focusing entirely on the output. With the schema already providing clear semantics, the description's lack of parameter info is acceptable.

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 indicates the tool returns 'the answers' for a campaign, and the title 'Campaign results' reinforces this. However, it lacks an explicit action verb like 'gets' or 'returns', making the purpose slightly inferential. It does distinguish itself from siblings by focusing on answer data, unlike other campaign retrieval tools.

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 does not explicitly state when to use this tool versus alternatives like get_campaign_details or analyze_campaign. It mentions that the AI report is included if analyze_campaign has run, but this implies a dependency rather than a usage guideline. There is no mention of when not to use it or which sibling to choose instead.

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