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

Annotations already declare readOnly=false, destructive=false, openWorld=true, so the mutation profile is covered; the description adds materially new context by flagging that the call is billable and that retries charge again unless the idempotency key is reused. It stops short of saying what happens to the original run's prior outputs or how to observe the new run.

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, zero filler, with the core action and its billing implication front-loaded before the retry hint. Nothing is wasted.

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?

There is no output schema, so the description carries the burden of return-value disclosure and omits it — an agent cannot tell whether it receives a new run_id to poll or a job handle. It also silently leaves the deprecated budget/levers sub-fields to the schema, which is acceptable but leaves the kickoff-to-observation workflow incomplete.

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%, including the step pattern, run_id format, and the idempotency-key semantics, so the baseline is 3. The description restates the idempotency key but adds no syntax, format, or interaction detail (e.g. step format, deprecated budget/levers fields) beyond the schema.

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 concrete verb+resource+scope: 'Create a billable rerun starting at a named pipeline step.' The 'starting at a named step' qualifier distinguishes it from a fresh start, though it never names the natural alternative (start_run) the way the clearest sibling pairs do.

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?

'Pass an idempotency key for safe retries' is a calling tip, not when-to-use guidance. There is no statement of when to rerun_from versus start_run, control_run, or simply polling run_status on the existing run, and no prerequisites or exclusions.

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