Call Actor

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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true, idempotentHint=false, and the description adds substantial context beyond them: waitSecs blocking behavior with non-terminal nextStep polling instructions, return of run status and storage IDs, dataset field metadata reporting when waitSecs > 0, memory quota rejection retry advice, and pay-per-result/event charge caps in callOptions. This is rich behavioral disclosure consistent with the 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 lengthy but well-structured with WORKFLOW, IMPORTANT, USAGE, and EXAMPLES headers. There is some redundancy: the 'There are two ways to run Actors' paragraph repeats the 'always use dedicated tools' and 'only if no dedicated tool exists' guidance that appears again in USAGE. Slight trimming would help, but every section earns its place given the tool's complexity.

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 tool with 4 parameters (one a nested object), an output schema, and complex runtime behavior, the description is remarkably complete. It covers prerequisites, MCP server actor invocation format, waiting semantics, result retrieval flow, polling for long runs, and edge cases like name resolution. With an output schema present, not explaining return values is acceptable.

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 baseline is 3. The description adds meaningful value beyond the schema: practical waitSecs guidance ('Default 30s returns results for fast actors. Use waitSecs: 0 to start and return immediately'), the workflow hint to fetch the input schema before calling, and the requirement to resolve non-'username/name' actor names via search-actors. It doesn't exhaustively document every callOptions field, but the schema already covers those.

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 opens with a specific verb+resource statement: 'Call any Actor from the Apify Store.' It clearly distinguishes itself from siblings by positioning dedicated tools as the preferred alternative and this tool as the generic dynamic path. References to fetch-actor-details, search-actors, and get-dataset-items for related workflow steps further differentiate it.

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?

Extremely explicit guidance: 'Always use dedicated tools when available' and 'Use the generic call-actor tool only if a dedicated tool does not exist for your Actor.' It also names the exact alternative for each step (fetch-actor-details for schemas, search-actors for name resolution, get-dataset-items for results) and gives a concrete when-to-use example (dynamically running any Actor without dynamic tool registration).

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