Run an Apify actor

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

Annotations indicate readOnlyHint=false and openWorldHint=true, so the description does not repeat those. It adds meaningful behaviors beyond annotations: 'Costs Apify credits' reveals a side effect not captured in annotations, and 'allowlisted' imposes a constraint on which actors can be run. No contradiction with annotations.

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?

The description is four concise sentences, each conveying essential information: action, return handles, cost, and alternative. It is front-loaded with the primary verb and avoids any redundancies or extraneous details. This is a model of efficient structure.

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?

The tool is a mutating, external operation with 5 parameters and an output schema. The description covers purpose, return handles, costs, and a usage alternative. Combined with schema descriptions for wait_secs and input, it gives sufficient context for selection and invocation. Gaps remain for memory_mb and timeout_secs semantics, but these are optional and have schema-specified ranges, making them less critical.

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 60%; input, actor_id, and wait_secs have descriptions, but memory_mb and timeout_secs lack them. The tool description adds only minor parameter context (e.g., 'explicit input object' already in schema), and does not explain the purpose or effect of memory_mb or timeout_secs. It doesn't adequately compensate for the schema gaps.

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?

Description clearly states the action: 'Start an allowlisted Apify actor with an explicit input object.' It identifies the specific verb (start), resource (Apify actor), and scope (with input object). It also distinguishes from siblings by noting it returns run_id and dataset_id handles for follow-up tools, and explicitly prefers scrape_url for simple page scrapes.

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?

The description provides an explicit alternative: 'Prefer scrape_url for simple page scrapes.' This tells the agent when not to use this tool. It also implies when to use it: when a more complex custom actor run is needed. Mentions of get_run_status/fetch_dataset_items/validate_dataset indicate the workflow where this tool is the entry point, offering clear context on usage.

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