get_conversion_performance

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. While 'Retrieves' implies a read-only operation, it does not explicitly state that the tool is non-destructive or safe to call without side effects. It also does not disclose any permissions, rate limits, or limitations on data scope. The description does give some expectation of output (conversion type, campaign, cost, value) but lacks explicit behavioral caveats such as default time ranges or the meaning of includePostView.

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 with no redundant words. The primary purpose is stated first, and the added detail about cost per conversion and conversion value is relevant and concise. It is efficiently structured and front-loaded, making it easy for an agent to scan.

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?

Without an output schema, the description should explain what the tool returns, which it does partially by mentioning conversion type, campaign attribution, cost per conversion, and conversion value. However, it omits details about defaults (e.g., includePostView default true, timeGranularity default ALL) and any filtering effects. For a tool with six parameters and no annotations, this is adequate but not fully complete, leaving some gaps for an agent to infer.

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%, so the schema already documents all six parameters. The description adds context by explaining that the tool breaks down conversions by type/action and attributes them to campaigns, which hints at the purpose of campaignIds and timeGranularity. However, it does not add specific meaning to individual parameters beyond what the schema states, so it does not elevate beyond the baseline.

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 uses a specific verb ('Retrieves') and a precise resource ('conversion metrics broken down by conversion type/action'). It further specifies that it shows which conversions are driven by which campaigns, including cost per conversion and conversion value. This clearly differentiates it from sibling tools like get_campaign_performance (which likely focuses on campaign-level metrics) and get_creative_performance (creative-level), making its purpose unambiguous.

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 usage for conversion-focused analysis but does not provide explicit guidance on when to choose this tool over alternatives such as get_lead_gen_performance or get_campaign_performance. There is no mention of when not to use it or any conditions that would select a sibling tool. The context is clear only by inference, not by explicit exclusions or alternatives.

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