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

Annotations only state the call is not read-only, not idempotent, and not destructive. The description adds two non-obvious behavioral facts: no USDC credit is granted, and the API key is shown in plaintext only once. This is critical operational context beyond what annotations convey.

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 one tight sentence containing the endpoint, the action, and two important caveats. Every clause carries information, and the most critical caveats ('Does NOT add USDC credit', 'Plaintext shown once') are front-loaded after the action.

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 one-parameter creation tool, the description covers the essential operational facts: endpoint, creation action, no credit grant, and single plaintext display. It does not detail the full response format, but 'Plaintext shown once' partially signals the return behavior, and there is no output schema requiring additional detail.

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?

Schema coverage is 100%, and the single 'name' parameter is already documented in the schema as 'Label for the new API key.' The description adds no parameter-level meaning, so it stays at the baseline for full schema coverage.

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 names the exact endpoint action ('POST /v1/agent/keys') and uses a specific verb+resource ('mint another key'), making creation unambiguous. It clearly separates this tool from siblings like list_keys and revoke_key without requiring schema inspection.

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 gives an explicit when-not: this tool does NOT add USDC credit, so it should not be chosen for funding workflows. It does not name an alternative tool like funding_instructions, but the negative guidance is enough to steer an agent away from a likely misuse.

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