backpressure

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and openWorld, so safety is covered. The description adds the nature of the returned figures (per-vertex average ms/s of backpressured/busy/idle time), but says nothing about aggregation window, rate limits, or that the cluster parameter selects across deployments.

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?

A single compact sentence with the metric front-loaded and the unit/breakdown immediately attached. No waste, though it could have spent a clause on the cluster parameter without becoming bloated.

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 structure need not be described, and annotations carry the safety profile. Still, with 0% schema description coverage the undocumented 'cluster' parameter leaves a real gap for a job-scoped metrics tool.

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 coverage is 0% and neither parameter is described in the schema. The description only implies job_id via 'for a job' and never explains the optional 'cluster' parameter, so an agent cannot tell what it does or when to supply it.

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?

States a specific metric (per-vertex backpressure) with units and components (avg ms/s backpressured, busy, idle) scoped to a job, which disambiguates the bare tool name 'backpressure'. It does not, however, differentiate itself from close siblings such as vertex_metrics or job_metrics.

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?

No guidance on when to use this versus vertex_metrics, job_metrics, or job_details, and no mention of prerequisites or when the metric is meaningful (e.g., during a diagnosed slowdown). The agent must infer selection from the name alone.

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