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

What was the annotation readOnlyHint=true already declares the tool is non-destructive, enabling the description to add value by listing exactly what data is returned: referral code/link, unlock status, tier and fee share, volume, earnings, referrer info, tier table, and program parameters. This goes well beyond merely restating the read-only trait and gives an agent a concrete picture of the operation.

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?

The description is a single dense sentence that front-loads the intent: 'status' is immediately specified and then each distinct category is listed. It is relatively long but every phrase conveys a separate meaningful field of the response, and no unnecessary filler is present.

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 zero parameters and no output schema, the description carries the full burden of telling an agent what the tool offers. It fully covers the returned information, including nested details like unlock thresholds, referral tier table, and fee caps. An agent can select and invoke this tool correctly without needing to open additional schema or infer missing behavior.

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 parameters, so the schema is trivially complete and there is no parameter ambiguity for an agent to resolve. The description does not add parameter-specific meaning because none exists, but it correctly compensates by describing the output structure, which is all an agent needs for calling this zero-argument tool.

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 a specific verb ('get') and a specific resource ('referral / affiliate program status'). It then enumerates the detailed components of that status (code, link, tier, fee share, volumes, earnings), which distinguishes it from any sibling tool. The title and initial clause leave no doubt about what this tool returns.

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 makes clear that this is the tool for querying the calling account's own referral/affiliate program information. It does not explicitly discuss alternatives or when not to use it, but because there is no obvious sibling for referral info, the context alone is clear and self-contained.

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