Sample

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds only that the renderer defaults to the 'model-recommended Cookbook renderer', a small but real behavioral detail. It omits any mention of generation cost, latency, determinism/seed behavior, or how sampling and num_samples affect output.

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 with no wasted words. Efficient, though brevity here trades away necessary detail for a tool this complex.

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 nested, multi-field sampling tool with 0% schema coverage, the description leaves most invocation-critical detail unstated. The output schema covers return values, but nothing tells the agent how to populate sampling, num_samples, or the target/renderer selection.

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% on a deeply nested request object. The description hints at 'target' (model or checkpoint) and 'renderer', but says nothing about sampling controls (temperature, top_p, top_k, max_tokens, seed, stop), num_samples, or include_logprobs, leaving most parameters undocumented in both schema and description.

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 ('Sample') and resource ('a base model or checkpoint'), which is clearer than the tautological title 'Sample'. However, it does not name or distinguish itself from the closest sibling, compute_logprobs, which also runs inference against a 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?

The description gives no when-to-use guidance or exclusions. An agent cannot tell from the text when to reach for 'sample' versus compute_logprobs, evaluate, or dataset_render_preview — all of which operate on models/checkpoints.

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