diagnose_campaign

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

The description transparently explains the core behavior—diagnosing the most likely failure layer and providing a fix order—and adds the important insight that deliverability issues can look like copy issues. Since no annotations are provided, it fully carries the burden, but it does not mention optional input behavior or any side effects, which are presumably absent.

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 two sentences, front-loading the key information in the first sentence and adding a memorable heuristic in the second. No extraneous details are present.

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 moderate complexity and lack of output schema, the description adequately explains the return value and the diagnostic categories. It does not specify the exact structure of the fix order, but this is likely sufficient for agent invocation. The missing channel parameter in the description is a minor 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?

The description adds meaning to four parameters by specifying they are percents and allows any subset, which aligns with the schema's optional fields. However, it omits the required `channel` parameter entirely, leaving a gap in parameter semantics. The schema has no descriptions, so this incompleteness is notable.

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 defines the tool's function as a diagnostic for campaign failure layers, specifying the inputs (open_rate, reply_rate, bounce_rate, acceptance_rate) and outputs (failure layer and fix order). It distinguishes itself from sibling tools by highlighting the unique value of distinguishing deliverability issues from copy issues.

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 implies its usage scenario: when you have campaign metrics and need to determine whether the issue lies in infrastructure, list, or message. The deliverability-masquerading warning provides a strong 'when to use' hint, but it doesn't explicitly name alternatives or exclusion criteria.

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