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

Adds substantial behavior beyond the annotations: the api_key is returned ONCE, the Bearer auth scheme needed for the full toolset, and the human verification step (owner opens email and types user_code). These are consequential traits the annotations (idempotent, non-destructive) do not 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?

A single front-loaded sentence whose state transitions are packed into an arrow chain. Every clause earns its place, with the primary action stated first and detail following.

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?

Given the state-machine complexity and auth implications, the description covers transitions, required actions, and the api_key handoff well. No output schema exists and the returns are still explained, but the park_ref input is left unaddressed.

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 description coverage is 0% for the single required park_ref parameter, and the description never defines it, its format, or where it comes from. Only the vague 'parked upload' phrasing hints at its meaning, leaving the parameter undocumented.

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 and resource ('Check a parked upload') that clearly separates it from siblings like yetty_status and yetty_login_status. The state-machine framing signals exactly what the tool reports on, though the term 'claim status' vs 'parked upload' is slightly loose.

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 an explicit decision tree per state: when parked, send yetty_signup; when awaiting-approval, the owner acts; when approved, reconnect with the api_key. This names the alternative action for at least one branch, though it never states explicitly when not to call it.

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