Retrieve recent Replicate account predictions with optional cursor pagination by providing an API token, so you can review prediction history.
List recent predictions for a Replicate account.
| Name | Required | Description | Default |
|---|---|---|---|
| cursor | No | ||
| api_token | Yes |
Changes observed during successful MCP inspections.
v0.1.9v0.1.5Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so safety behavior is covered. The description adds useful scoping with 'recent' and 'for a Replicate account,' but it does not explain pagination, rate limits, or what the token authorizes. With annotations carrying the main behavioral burden, a 3 is appropriate.
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 a single front-loaded sentence with no redundant or wasted wording. It immediately communicates the operation and scope.
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 exists, and both parameters lack descriptions in the schema, so the description carries more burden. It does not explain the required api_token, the optional cursor, pagination behavior, or what a prediction listing contains. It is therefore too thin for an agent to invoke confidently beyond the basic intent.
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 0%, and the description does not explain either parameter. The phrase 'for a Replicate account' weakly implies that api_token identifies the account, but cursor is completely undocumented, leaving pagination behavior unclear. For a low-coverage schema, the description should compensate more than this.
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 states a specific verb and resource: 'List recent predictions.' The scope is further narrowed to a Replicate account, making the operation clear. It does not explicitly name siblings such as replicate_get_prediction or replicate_list_models, so it stops short of full sibling differentiation.
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 gives no explicit guidance on when to use this tool versus alternatives like replicate_get_prediction, replicate_create_prediction, or replicate_cancel_prediction. The listing intent is implied by 'List recent predictions,' but no conditions, exclusions, or alternatives are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.