get_stuck_handoffs

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

Beyond the readOnlyHint and idempotentHint annotations, the description explains the algorithm step-by-step, including the critical behavior that items with fresh comments but no state change are surfaced as stuck. It also clarifies the output grouping by transition pattern, which is valuable behavioral context not available in the schema or annotations.

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 structured effectively: a one-sentence definition, a differentiation paragraph, a numbered algorithm, an output description, and a parameter list. It is detailed but every section serves a purpose, and the most critical information (purpose) is front-loaded. There is no redundant filler.

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 complexity (6 parameters, nuanced algorithm), the description is complete. It covers the business problem, the exact detection logic, the output format, and all parameter semantics. Since an output schema is present, the description doesn't need to repeat return field details, but it explains the grouping concept sufficiently.

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?

Although the input schema has 0% description coverage, the description's Args section fully documents each parameter: board_name (partial match, ID, or URL), stuck_days (default 4), lookback_days (default 30), limit (default 10), format (report vs json), and instance (optional). This compensates completely for the schema's lack of descriptions.

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 a clear, specific definition: 'Tasks that crossed a team boundary and haven't moved since.' It names the resource (stuck handoffs) and the action (get), and explicitly distinguishes itself from sibling tools by explaining their different scopes and behaviors, leaving no ambiguity about what this tool does.

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 explicitly states when to use this tool vs alternatives: 'Distinct from get_handoff_snapshot... and track_cross_dept_journey...' It explains what those alternatives do and why this one is different, providing clear guidance on selection. It also implies the use case (identifying stuck handoffs) effectively.

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