Yarn Utilization Report

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

With no annotations, the description must carry the behavioral burden. It does disclose substantive behavior beyond the schema: the report aggregates average and peak values, breaks results down by tenant_type (POOL vs USER), reports idle capacity and contention waiting, and can be time-sliced. It does not state that this is a read-only/aggregation operation, whether large ranges are expensive, or any auth/permission requirements.

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 purpose and report contents are front-loaded, followed by a compact parameter-format block separated by a colon. Sentences are dense but each carries content, with the only mild redundancy being the parenthetical cross-reference to the 'Cluster Utilization Report'.

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?

An output schema exists, so return shape need not be described, and the description instead spends its space on content and time-window semantics, which is the right allocation for a reporting tool. The unresolved 'days'/'days_of_week' distinction and the undefined 'service' parameter are the main residual gaps, but they are parameter-level rather than framing-level omissions.

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 must compensate, and it does for start_hour/end_hour (0–23, with a business-hours example), days_of_week (format '1,2,3,4,5', 1=Monday), and tenant_type (POOL = per queue, USER = per user). However, three parameters remain opaque: 'days' (an integer defaulting to 7, plausibly a lookback window that could easily be confused with days_of_week), 'cluster' (required but unqualified), and 'service' (purpose unstated).

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 names a specific report (YARN utilization via CM) and enumerates its contents: average/peak cluster usage, per-queue (tenant_type='POOL') or per-user ('USER') memory/vcore allocation and usage, idle capacity, and contention waiting. That is a concrete verb+resource statement. It does not, however, differentiate itself from close siblings such as yarn_cluster_metrics or yarn_queue_usage, instead cross-referencing a UI report name ('Cluster Utilization Report') that is not a sibling tool.

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?

Usage context is only implied through parameter examples — start_hour/end_hour for business hours 8–18, days_of_week for weekdays only — which suggests when this report is useful. There is no explicit statement of when to prefer this over yarn_cluster_metrics, yarn_queue_usage, or yarn_top_consumers, and no exclusions or prerequisites.

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