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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive, closed-world), so the bar is low. The description still adds real behavioral value by describing the aggregate return shape and the cost accounting model — machine time per attempt, summed in USD to six decimals — which no structured field supplies and which materially affects how an agent should interpret cost_usd.

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?

Two sentences, front-loaded with the resource and the return fields, ending with the sibling cross-reference. The cost clause is dense (appositive inside a list) but every phrase earns its place; tighter punctuation would help readability.

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?

With no output schema, the description does the work of explaining the returned counters and cost field, and the fully-covered schema handles parameters. Only minor gaps remain: nothing about ordering, missing groups, or how cost_usd behaves for still-running jobs.

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 100%, so the schema already explains id, workspace, and environment including their defaults. The description adds no parameter-level semantics beyond noting the id corresponds to a group's group_id; baseline 3 is appropriate when the schema carries the burden.

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 and resource ('Get a group of jobs'), specifies the origin of that group ('started by run_job with count or params'), and enumerates what comes back (status_counts, max_parallel, cost_usd). It also names the sibling that serves a different need ('list_jobs with group_id'), so an agent can separate it from get_job/list_jobs without opening schemas.

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?

It gives a clear routing rule: use list_jobs with group_id when you want the individual jobs, implying this tool returns the aggregate view. It never explicitly states when this tool is the wrong choice versus get_job or cancel_job_group, so there is no true when-not guidance, but the context is unambiguous.

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