get_prediction

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

Annotations already provide readOnlyHint=true, so the agent knows this is a safe read operation. The description adds the recovery use-case context but doesn't disclose additional behaviors like error handling, response structure, or rate limits. With annotation coverage, a 3 is appropriate.

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?

One sentence, no redundancy, completely front-loaded with the core action and purpose. Every word earns its place.

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 simple single-parameter read-only tool with annotations covering safety, the description fully conveys what it does and when to use it. No output schema exists, so explaining 'status and outputs' is sufficient.

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?

The single parameter 'id' is fully described in the schema ('Prediction id returned by run_model'), achieving 100% coverage. The description adds no extra semantics but also doesn't need to since the schema is clear. Baseline 3 applies.

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 clearly states the tool fetches the status and outputs of a prediction by id, using the specific verb 'fetch' and resource 'prediction'. It also includes a specific use case (recover from wait limit) that distinguishes it from siblings like run_model.

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 explicitly says 'use to recover a run that hit the wait limit', giving a clear context when to use. It doesn't mention when not to use or name alternatives, but the purpose is unique among siblings (list_models, run_model, etc.), so the guideline is clear.

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