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

Annotations already declare a safe read, yet the description adds genuinely new behavior: keys are write-only and never returned, a workspace-settings-read credential is required, and a self-registered sandbox key is refused with 403 until the workspace is claimed. That 403/claim nuance is exactly the kind of failure mode an agent cannot infer from schema or annotations.

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?

Three short sentences, each carrying distinct load (capability, non-return of keys, auth prerequisites). Mildly dense phrasing in 'pricing functions that run on a model' but nothing is wasted or repeated.

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?

With no output schema, the description does convey the shape of what comes back (connected providers plus key-storage availability), and it covers auth and workspace-claim gating. A brief note on ordering or pagination is the only omission, and with zero params that is minor.

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 schema baseline is high; there is nothing parameter-related to compensate for and the description correctly does not invent any. No credit for extra parameter meaning is possible here.

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?

Uses a specific verb+resource: lists model providers connected to the workspace and whether key storage exists. It implicitly distinguishes itself from inventory-style siblings like list_hosted_models by scoping to 'providers ... for pricing functions that run on a model', but never names an alternative explicitly.

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?

Gives concrete when-to-use signals (checking connection status and key-storage availability) and an implicit when-not ('Status only: the keys are write-only and never returned') that steers agents away from using it to retrieve credentials. Prerequisites are spelled out, but no sibling tool is named as the alternative for the adjacent task.

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