Yarn Top Consumers

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

With no annotations, the description carries the full burden and does substantial work: it discloses that both running and finished applications are aggregated, that accumulated GB-hours/vcore-hours are combined with instantaneous usage of running apps, and the important caveat that apps started before the window count entirely. It omits permission requirements and the behavior when the underlying app set is capped (max_apps), which keeps it from a 5.

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 front-loaded with the core operation, then aggregation semantics, then a compact parameter block, then a caveat. Each line carries information, though the parameter list reads like a schema restatement in places and could be tightened.

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 values needn't be described, and the core aggregation behavior is well covered. But for a 9-parameter tool with zero schema coverage and no annotations, leaving top, max_apps, service, and cluster undocumented — plus no mention of cost or result-size implications — leaves real gaps an agent could stumble on.

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; it meaningfully documents group_by ('user' or 'queue'), rank_by with units for each value (memory/vcores/apps/current_memory), and the user/queue filters — value semantics the schema lacks since no enums are declared. However, four of nine parameters (top, cluster, service, max_apps) get no explanation at all, and max_apps in particular could silently truncate results without the agent knowing.

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 operation — ranking YARN consumers aggregated over a time window — with the resource (memory GB-hours, vcore-hours, app counts) and the two grouping modes named explicitly. An agent can tell this apart from sibling list-style tools such as yarn_list_applications or yarn_queue_usage because the aggregation/ranking behavior is stated up front.

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 is only implied through parameter choices: 'group_by: user ou queue' and the rank_by options signal when each mode is appropriate, and the default grouping is called out. There is no explicit statement of when to prefer this over yarn_utilization_report, yarn_queue_usage, or yarn_list_applications, and no when-not-to-use conditions or prerequisites.

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