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

Annotations already carry the safety profile (readOnly, idempotent, openWorld, non-destructive), lowering the bar. The description adds behavioral value with 'currently' and 'staged,' signaling the catalog is dynamic and includes not-yet-available paid families. No contradiction with 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?

A single front-loaded sentence with the verb first and zero filler. Every word ('currently', 'exposed', 'staged') earns its place by adding scope or timing information.

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 0-parameter read-only discovery tool with a rich annotation set, nothing an agent needs to invoke it correctly is missing. Safety and idempotency are covered by annotations, and the return value (a list of tools/families) is self-evident from the description.

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 description bears no burden of explaining inputs — baseline 4 applies. The description's specification of what gets listed further orients the agent beyond 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?

The description uses a specific verb ('List') and a concrete resource ('GhostKey's currently exposed tools and staged paid families'). The scope clearly distinguishes it from siblings ghostkey_policy, ghostkey_quote, and ghostkey_status, which concern specific individual concerns rather than a catalog of available tools.

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?

Usage is implied: an agent needing to discover what tools exist would naturally call this. However, the description gives no explicit when-to-use or when-not-to-use guidance, and it never references the sibling tools, so routing depends on inference rather than stated direction.

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