get_class_performance

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

No annotations are provided (e.g., readOnlyHint, destructiveHint), so the description carries the full burden of disclosing behavioral traits. The description only says 'Rank classes by fill rate' but does not disclose whether this is a read-only operation, whether it performs any calculations or aggregation, or whether any side effects exist. For a read-only reporting tool, even a phrase like 'Returns a list' would help, but it is missing. The description does not contradict any annotations (since none exist), but it fails to convey expected behavior beyond the high-level result.

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 sentence, highly concise, and immediately communicates the core purpose. It is front-loaded with the action 'Rank classes' and provides a practical implication ('popular vs. dead classes to cut'). No unnecessary words or repetition. It is appropriately sized for its simplicity.

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 simplicity (one parameter, no output schema), the description covers the main intent well. However, it lacks details about the return type (e.g., does it return a list with fill rates?), how 'limit' affects results, and whether it includes only active classes or all classes. Since there is no output schema, the description should provide some indication of what the tool returns. The description is adequate for a simple read-only tool but is not comprehensive for an agent that might need to interpret results.

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?

There is one parameter, 'limit', which has a default and no description. Schema description coverage is 0%, but with only one parameter, the description's mention of 'Rank classes' implies that 'limit' likely controls the number of classes returned. However, the description does not explicitly explain the 'limit' parameter, so an agent might not know if it controls the number of classes or something else. While the single parameter is self-explanatory to a human, the description adds no specific explanation, so the agent must infer from the schema's default value.

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's purpose: to rank classes by fill rate, identifying popular and dead classes for potential cutting. The verb 'Rank' and resource 'classes' are specific, and the purpose is distinct from siblings like 'get_today_summary' (which likely provides a summary) and 'get_revenue_insights' (which focuses on revenue). However, it does not explicitly mention the return format or the scope of data (e.g., current vs. historical), so it is not perfect.

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 planning class cuts or evaluating class performance, but it does not explicitly state when to use this tool versus alternatives. For example, it does not say 'Use this when you need to identify underperforming classes' or 'Instead of get_revenue_insights, use this for class-level fill rates.' The guidance is minimal and relies on inference.

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