Yarn Queue Usage

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

With no annotations supplied, the description carries the full burden and does well: it discloses the underlying data source (CM time-series, YARN_POOL category), notes that fair share is only present conditionally on Fair Scheduler being in use, and gives an interpretation rule for the 'pending' metric. It does not mention permissions, latency of the time-series query, or whether results are aggregated per queue, but the core behavioral picture is clear for a read-only metrics tool.

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 content is front-loaded: the resource and metric set come first, followed by the contention hint and the parameter note. Every clause adds information. The main friction is a language mismatch — the body is Portuguese while the name, title and sibling tools are English — plus one run-on sentence enumerating metrics.

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-value explanation is not required, and the description is reasonably complete on the measurement side. The gaps are the unexplained 'service' parameter and the absence of any annotation coverage for a tool that queries a time-series backend; those keep it at adequate rather than complete.

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% across three parameters, so the description must compensate. It explains only 'minutes' ("janela para calcular o pico"), while 'cluster' is inferable from its name; 'service' is entirely undocumented — its meaning in a YARN-queue context and the effect of leaving it null are left to guesswork, which matters given additionalProperties=false.

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 resource (each YARN queue's current and peak usage) and enumerates the exact metrics returned: allocated/pending/available memory and vcores, running/pending apps, and fair share when the Fair Scheduler is active. It also discloses the data source (Cloudera Manager time series, YARN_POOL category), which distinguishes it in substance from siblings like yarn_cluster_metrics or yarn_scheduler_queues, though it never names those alternatives explicitly.

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 implied rather than stated: the note that "'pending' > 0 indica fila sob contenção" tells the agent what to look for when diagnosing contention, which is genuine guidance. However, there is no explicit when-to-use versus yarn_scheduler_queues or yarn_cluster_metrics, and no stated prerequisites or exclusions.

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