run_prediction

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

With no annotations, description discloses default waiting behavior and async option via wait_for_result parameter. However, it omits authorization needs, error handling, or whether the operation is idempotent. The auto-resolution detail adds some transparency.

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 sentences, front-loaded with purpose, then concise behavioral details. No redundant or irrelevant content.

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?

Given 7 parameters, 2 required, and a nested object, the description is partially complete. It covers key behaviors but lacks detail on input_data format and other parameters. Output schema exists, so return values are not needed in description, but further guidance on parameter usage would improve completeness.

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 coverage is 0%, and description only explains project_id, target_feature (auto-resolved), and wait_for_result. It does not clarify input_data as a nested object, max_wait_seconds, poll_interval_seconds, or model_version_id. This leaves most parameters underspecified.

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?

Description clearly states 'Run a single ad-hoc prediction against a trained model version,' which includes a specific verb and resource. It distinguishes from siblings like run_batch_prediction by specifying 'ad-hoc' and 'single prediction.'

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?

Description explains auto-resolution of project_id and target_feature, and the wait_for_result option to control synchronous vs. asynchronous behavior. While it doesn't explicitly contrast with alternatives, the context implies usage for one-off predictions.

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