vertex_metrics

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real behavioral detail beyond them: results are aggregated over subtasks as min/max/avg, and the no-names call switches to an id-listing mode rather than a value call. The prefix-matching rule for names is also disclosed. Cluster/auth behavior is left unstated.

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?

Three dense sentences with no filler, and the core scope is front-loaded. The id-listing mode and the prefix rule are packed into parentheticals, which is efficient but slightly terse on first read.

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 needn't be spelled out, and the description still covers the aggregation semantics and mode switch. For a 5-parameter tool the only unaddressed element is the cluster parameter's meaning and default behavior.

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?

With 0% schema description coverage the description must carry the params, and it covers names (optional, prefix-omissible), search (narrows id listing), and vertex_id (sourced from job_details). job_id is implicitly the job selector; cluster is not explained anywhere, which is the remaining gap.

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 verb+resource: operator/task metrics for a job's vertices, with explicit scope (all vertices or one vertex_id). It also distinguishes itself from job-level metrics by naming the vertex level and the aggregation form (min/max/avg over subtasks).

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?

Explains two modes explicitly: without names it enumerates metric ids (narrow via search, with an example "lag"), with names it returns values. It also points to job_details as the source of vertex_id, giving a workflow cue. It stops short of naming sibling alternatives such as job_metrics vs vertex_metrics for the when-not case.

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