llm_analytics

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 disclosing behavioral traits. The term 'analytics' and 'aggregated stats' imply a read-only, non-destructive operation, but the description does not explicitly state this, nor does it mention auth needs, rate limits, or what the response contains. It does not contradict anything, but it leaves significant behavioral aspects undocumented.

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 compact and well-structured: it opens with the tool's purpose, lists views in a scannable format, and then provides parameter usage notes. Every sentence adds value without redundancy or unnecessary detail, making it easy to parse quickly.

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 has 7 parameters, no output schema, and no annotations, the description should cover more ground. It thoroughly explains the view logic and some filters, but omits the purpose of required site_global_key and the date-range parameters, and provides no indication of the return format or data structure. Overall, it is not fully complete for such a complex tool.

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 several parameters: it enumerates the possible values of 'view', clarifies that 'metric' is used for non-stats views, and explains that llms_list/channels_list are comma-separated filters applicable to stats/performance views. However, it does not explain to_date, from_date, or site_global_key, which is a notable gap given the schema has 0% description coverage.

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 the tool provides LLM traffic analytics and enumerates multiple views, each with a specific purpose (stats, performance, channels, etc.). This distinguishes it from sibling tools like serp_analytics, which focus on search engine data. The verb+resource is explicit and 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 offers clear context on how to use different views and parameters (e.g., metric for non-stats views, filtering for stats/performance), but it does not discuss when to use this tool versus alternative analytics tools, nor does it mention any exclusions. Usage guidance is implied rather than explicitly framed as a choice among siblings.

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