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

Goes well beyond the readOnly/idempotent annotations: it discloses the feature-gate behavior (released: false with no models, and every other hosted model tool 404 not_released), the required credential scope (function read), and the claimed-workspace requirement with the exact 403 failure for self-registered sandbox keys. That is exactly the kind of failure-mode context an agent cannot infer from structured fields.

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?

Front-loaded with the core definition, then return fields, then feature-gate and auth caveats. Every sentence carries information, though the embedded JSON inference-config example and the double auth sentence make it denser than strictly necessary for a zero-arg list call.

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?

No output schema exists, and the description compensates by describing the return payload (per-model fields plus limits, ONNX operators, and readable request fields). With gating, auth, and the pricing-function linkage all covered, an agent has everything needed to call this and interpret the result.

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 tool takes zero parameters, so the 4 baseline applies; the description correctly spends no words on parameter syntax. It does add meaning about the response shape, though that registers under completeness rather than parameter semantics.

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 concrete verb and resource plus scope ('your workspace's hosted pricing models'), and defines what a hosted model is (trained here on quote outcomes or uploaded as ONNX). It also enumerates the fields returned (id, name, kind, active/latest version, nightly retrain flag), which cleanly separates it from single-record siblings like get_hosted_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?

Implies the use case clearly by noting the returned model ids are what a pricing function references in its inference config ({"provider": "last-price", "model": "<model id>"}), so an agent knows to call this before wiring a function. It stops short of explicit exclusions or naming alternatives such as get_hosted_model or create_hosted_model.

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