replicate_list_predictions

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

Without annotations, the description must cover behavioral traits. It only says 'recent' without defining recency, omits that the api_token is required, and does not disclose the effect of cursor on pagination or the fact that listing is read-only.

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 sentence, which is concise and front-loaded. However, it sacrifices necessary detail, making it slightly under-specified for a 2-param tool with no annotations.

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 has two parameters, no output schema, and a sibling set including creation and single-get. The description fails to clarify the output format, explain pagination via cursor, or differentiate its scope from other prediction tools. It is not complete enough for reliable use.

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%, yet the description adds no explanation for 'api_token' or 'cursor'. It repeats the parameter names implicitly but provides no additional semantic context beyond what the schema already shows.

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 clearly states 'List recent predictions for a Replicate account.' The verb 'list' and resource 'predictions' are specific, and it differentiates from siblings like 'replicate_create_prediction' (create) and 'replicate_get_prediction' (single).

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?

No usage guidance is provided. The description does not mention when to list vs. get a specific prediction, nor does it explain pagination or the role of the cursor parameter. The agent receives no cues about alternatives.

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