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

Annotations already convey readOnlyHint=truehareliability/openWorldHint=true, and the description adds useful behavioral context: it does not consume allowance and it may return action_required with links that must be relayed. This enriches the agent's understanding beyond what annotations alone provide.

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?

Four short sentences, each adding new information: what it returns, side-effect free behavior, when to call it, and how to handle results. It is front-loaded with the core purpose and ends with an actionable, memorable instruction.

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 zero-parameter read-only tool with no output schema, the description covers the essential return facets and the required follow-up behavior. It does not enumerate all possible response fields, but the action_required case is sufficiently specified for an agent to act correctly.

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 has zero parametershare, so a baseline of 4 is appropriate. The description confirms the call requires no inputs by focusing entirely on outputs and usage, which is consistent with the empty schema.

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 ('Returns'), a clear resource ('this connection'), and the concrete data it exposes: signed-in status, annual product access, and remaining calculations. It also distinguishes itself from sibling compute tools by explicitly noting it does not consume allowance.

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?

Provides explicit when-to-use guidance: call it before a compute tool when unsure the user can run one. It also gives post-call handling instructions for the action_required case spiders. It does not explicitly name alternative sibling tools, so it stops short of a full when-not-to-use statement.

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