qobrix_win_loss

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

With no annotations provided, the description carries full behavioral disclosure. It goes well beyond a simple summary by exposing the exact win_rate_pct formula, the windowing fallback (last_status_change then modified), the scope of global returns, the multi-dim grouping capability, and the extra data delivered by include_top_losses. This is exceptionally transparent and sets clear expectations.

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 but dense. It starts with a clear one-sentence summary, then explains the return payload, optional grouping, and window behavior, followed by five illustrative examples. Every sentence carries useful information, though the example list makes it slightly longer than necessary. Still, it is well-structured and easy 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?

For a tool with 9 parameters, no output schema, and no annotations, the description is remarkably complete. It covers the main output metrics, the windowing semantics, grouping options, multi-dim support, the optional top-losses payload, and practical usage patterns. An agent could confidently invoke this tool and correctly interpret results without additional documentation.

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%, but the description adds substantial meaning beyond individual parameter descriptions. It explains how parameters interact (e.g., group_by valid values, multi-dim arrays), defines the window fallback, clarifies that 'CLOSED' maps to assigned_to, and shows real parameter combinations via examples. This transforms the bare schema into a rich usage model.

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 opens with 'Win-rate analytics over opportunities,' a specific verb+resource phrase that clearly distinguishes this tool from sibling tools like qobrix_deals or qobrix_funnel. It further specifies exactly what it returns (counts, win_rate_pct, optional top losses), leaving no ambiguity about its purpose.

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 provides multiple concrete example use cases ('Overall 2026 win rate,' 'Win rate by lead source,' 'Top loss reasons last 90 days,' 'My win rate,' 'Forensic loss review') that clearly imply when to use the tool. However, it does not explicitly name alternative tools or state when NOT to use this tool, so it misses the top tier of usage guidance.

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