scenario_step

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

With no annotations the description carries the full burden, and it does well: it discloses the safety constraint that apply requires the owner's explicit yes for this specific step, that runs are persisted and resumable via retry, and that the call returns what happened plus the next pending step.

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?

Front-loaded with the core action and packed with meaning; the parenthetical glosses on each decision earn their place. Dense and slightly run-on, but no wasted sentences.

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?

No output schema, but the description covers return values and persistence. However it omits how a 'run' is obtained (presumably from scenario_start) and how params (nested object) interacts at call time beyond the schema note, leaving a gap for a mutation tool with no annotations.

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 only 33%, so the description must compensate. It richly explains the decision enum (apply/done/skip/retry), which is more than the bare enum, but the required 'run' parameter is left unexplained in both schema and description — where a run id comes from is never stated.

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: answering the step a run is waiting on, and names the four decision values with their meanings. An agent can tell this is the step-resolution tool distinct from scenario_list/scenario_start, though it never explicitly names those siblings.

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 when each decision applies: apply only with the owner's explicit yes, done for a manual step the owner finished, retry to re-check/re-plan. This is clear per-decision guidance, but it gives no explicit routing rule versus scenario_start or scenario_list.

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