List predictions

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds the useful behavioral fact that results come newest-first, but says nothing about pagination, result limits, or how an empty project_id behaves.

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?

Two short sentences, no filler, with the ordering guarantee and optional filter front-loaded before the alternative-tool pointer.

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 one-parameter listing tool with an output schema (so return shape need not be explained) and full annotation coverage, this is nearly complete. The only missing pieces are pagination behavior and the meaning of the empty default project_id.

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 parameter burden. It does name the sole parameter and marks it optional, but adds no format details or behavior for the default empty string (presumably 'return all projects'), leaving a genuine gap.

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 ('List predictions') plus the ordering guarantee ('newest first'), which no sibling name conveys. It also explicitly distinguishes itself from the sibling get_prediction, which retrieves a single record.

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 says to use get_prediction(id) when the caller needs the full result plus a batch download URL, which is a concrete routing rule. However, it does not state when NOT to use this list (e.g., for unpaginated bulk exports) or how it relates to run_prediction/run_batch_prediction.

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