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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so safety is covered. The description goes beyond them by disclosing return content — the full status vocabulary (starting/processing/succeeded/failed/canceled), output URLs, and logs — which is genuinely useful for a polling agent, though it says nothing about polling cadence or rate limits.

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 well-formed sentence with the action front-loaded and the return payload trailing; no filler.

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 carries the return-value burden and does so adequately by enumerating statuses and outputs. What is missing is polling behavior guidance, which matters for a status-check tool.

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 single parameter has no schema-level description. The description only clarifies that the id refers to a Replicate prediction, adding marginal meaning but no format or provenance details for the id.

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 names a specific verb pair (poll/retrieve), the resource (a Replicate prediction) and the lookup key (by id), which cleanly separates it from siblings such as create_prediction, cancel_prediction, and list_predictions. An agent can route to this tool without opening any schema.

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 word 'poll' implies this is used after a prediction has been created, but no alternative is named and there is no when-not guidance (e.g., use list_predictions for enumeration, cancel_prediction to stop a run). Usage is inferable but not stated.

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