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

Annotations only declare safety/identity hints (readOnlyHint=false, idempotentHint=true, non-destructive), so the description carries the real behavioral load. It discloses a genuinely important trait: the api_key is returned ONCE, plus the meaning of the pending state ('owner has not typed the code yet'). It omits expiry/polling-limit behavior for the pending state, so not a 5.

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 state semantics are front-loaded in the first clause, which is the right order. The reconnect shell command is long and could arguably live in a doc, but it is concrete and immediately actionable rather than filler.

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 single-parameter, no-output-schema tool, the description covers the return value (api_key once) and the action to take afterward, which is what an agent actually needs. The only gap is where login_ref originates and what to do if the status never leaves pending.

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% and login_ref is undocumented in both schema and description; the reader must infer it comes from yetty_login. With one required parameter and no compensation in prose, the description falls short of the baseline it would otherwise enjoy.

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 an email sign-in') and describes the state progression (pending -> approved), which tells the agent what the tool observes. It does not explicitly differentiate itself from siblings like yetty_login or yetty_claim_status, which is the only thing keeping it from a 5.

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 rather than stated: the pending->approved framing suggests polling after initiating a sign-in, and the reconnect example implies the tool is called to complete setup. There is no explicit 'call this after yetty_login' or 'do not use for X' guidance, and no named alternative among the nine siblings.

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