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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered structurally. The description adds real behavioral context beyond them: the list is ordered newest first and the account scope is implied, though return shape and pagination are left to the output schema.

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 covering both modes with no filler; the id-vs-list choice comes first and the archived nuance is parenthesized at the end. The interjected '— the poll —' is slightly cryptic and costs a bit of crispness.

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 an output schema present, return values need not be explained, and the description covers both invocation modes, the archived filter, and ordering. It does not mention pagination limits on the list mode, a minor omission for a two-param read 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%, so the description has to carry both parameters, and it does: prediction_id selects one prediction and archived switches the listing to archived items (implying the default lists non-archived). The one gap is that it never states the explicit default value for archived.

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 uses a clear verb+resource ('Read one prediction by id') and covers both the single-item and list modes, which distinguishes it from mutating siblings like predict_virality, archive_virality_prediction, and delete_virality_prediction through the tool name and read framing. It never names a sibling explicitly, so the differentiation relies on inference from the verbs.

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?

It gives condition-based routing: supply prediction_id for a single prediction, omit it to list, and set archived: true for archived items. What is missing is an explicit when-not boundary against predict_virality (the create path) or archive_virality_prediction, so the agent must infer those distinctions.

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