track_cross_dept_journey

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, which cover the safety profile. The description adds valuable behavioral context beyond those: it discloses that departments are 'auto-detected from project shortnames using generic role-based patterns', explains the semantics of thresholds (stale_days and avg_window_days), mentions how subtasks are included, and caps issues fetched (max_issues). This adds the behavioral nuance an agent needs for accurate invocation.

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: a one-sentence overview followed by the Args list with per-parameter explanations. It is front-loaded with the primary purpose and the behaviors follow logically. The formatting is clear and the content earns its place; the 'Args:' section is a little long but necessary for parameter semantics.

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?

The description covers the critical operational details for a moderately complex tool with 6 parameters and output schema present. It explains behavior (detection, thresholds, subtask inclusion, cap) and parameter usage. The exact output format is delegated to the output schema, but the description could have briefly mentioned return types or pagination/analytics aggregate vs per-issue detail; however, the output schema presumably fills that. Overall it is nearly complete, with only a minor omission of an explicit mention that the journey is per issue versus aggregated.

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 0%, so the description carries the full burden of explaining parameters. It does so thoroughly: each parameter is described with semantic meaning and intended usage (e.g., query as a YouTrack selector, stale_days for flagging current station, avg_window_days for rolling averages, follow_subtasks for hierarchy inclusion, max_issues cap, and an optional instance). The inclusion of a query example adds practical clarity far beyond the schema titles.

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 states a specific verb and resource: 'Track cross-department handoffs' followed by concrete outputs ('bottlenecks, dept load, avg transit times'). It clearly distinguishes itself from siblings like get_handoff_snapshot and get_stuck_handoffs by building 'a chronological journey of dept changes' per issue, which is a unique, specific purpose. An agent can select it without ambiguity.

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 does not explicitly state when to use this tool versus alternatives, nor does it give exclusion conditions. However, the intent is decently implied by the purpose statement and the parameter example ('e.g. project: PROJ #Unresolved'), suggesting it is used for analytical cross-department journey reporting. No explicit 'when not to use' guidance is present, leaving this at an adequate but not strong level.

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