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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=true), so the bar is lower. The description adds useful return/workflow context (prediction id and status, polled via the prediction tool) but never explains the non-obvious idempotency guarantee or what auth/quota constraints apply.

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, return value, and next step with no filler. Nothing wastes space.

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?

With no output schema the description correctly states what is returned (prediction id and status). However, for a 5-parameter tool with 0% schema coverage and webhook/stream options that materially change behavior, the definition leaves important capability surface unexplained.

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%, so the description must carry the load, yet it only accounts for the two required params ('version id and input object'). It says nothing about the three optional params (stream, webhook, webhook_events_filter), leaving them documented only implicitly through schema examples.

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?

States a specific verb and resource ('Start a Replicate model run') plus the required inputs ('version id and input object'), which is clear. It does not, however, differentiate itself from the very similar sibling create_deployment_prediction, so the agent must infer which one owns a given use case.

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 follow-up guidance ('can be polled with the prediction tool until output is ready'), which implies the intended workflow. It offers no explicit when-to-use-this-vs-alternatives guidance, notably omitting any contrast with create_deployment_prediction.

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