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

Annotations already cover safety (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description nonetheless adds real behavioral context beyond them: ordering (reverse chronological), pagination mechanics (cursor), and the fields returned. It omits any page-size limit or what the cursor's absence means.

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?

A single front-loaded sentence that packs purpose, ordering, pagination, and return shape with no filler. Every clause earns its place.

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 read-only, single-optional-parameter list tool with rich annotations and no output schema, the description supplies the return fields and paging model an agent needs. Only minor paging-edge details (page size, end-of-list behavior) are absent.

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% for the single `cursor` parameter, so the description must compensate. "Paginated via cursor" does convey the parameter's purpose and the paging direction, but it never explains the cursor's format, where it comes from, or that omitting it fetches the first page.

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 pairs a specific verb ("List") with a specific resource ("your recent Replicate predictions") and adds scope ("reverse chronological order"), so an agent can distinguish it from create_prediction, cancel_prediction, and prediction. It does not explicitly name a sibling to route against, so it falls short of a 5.

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?

Usage is implied by the verb and the "recent/paginated" framing, but there is no explicit when-to-use guidance, no condition that selects this over the sibling `prediction` (likely a single-prediction fetch), and no statement about what happens when the list is empty. Adequate but with clear gaps.

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