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

Annotations only give the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds the actual state effects the annotations cannot express: the run's position is unchanged, the next step comes into hand, and the deferred step is reordered. It also explains that expectsStep is an optimistic-concurrency guard ('make sure nothing else moved it first'), which is behavior an agent needs before calling.

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 tight sentences with no filler, but the leading clause 'Not now, for the step a run is on' is the least informative part and occupies the front-loaded position, forcing the reader past it to reach the useful enum semantics.

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?

For a 3-parameter mutation with no output schema and full schema coverage, the description covers effect and concurrency guard adequately, but omits what happens if expectsStep mismatches, whether step history is recorded for the deferred step, and what the call returns.

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 100%, so the baseline would be 3, but the description genuinely adds meaning: it clarifies what `later` and `last` do to the step in the run's ordering and reframes expectsStep as a guard against concurrent modification, which the schema only describes neutrally as 'the id of the step the run should be on.'

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 conveys that the current step is postponed rather than skipped, then defines the two modes: `later` moves it one place down, `last` to the end. However, the opening phrase 'Not now, for the step a run is on' is oblique and never names the resource explicitly as a step-ordering operation, so the agent has to infer the verb+resource from the enum meanings rather than reading it directly.

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?

There is an implied condition ('not now'), but no explicit statement of when to choose this over adjacent tools such as next_step, pause_run, or stop_run, all of which are plausible alternatives for the same situation. No exclusions or prerequisites are given.

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