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

Annotations already declare it is a non-read-only, non-idempotent, non-destructive, closed-world operation, and the description is consistent with that (it starts a pairing session, not a plain read). It adds useful lifecycle detail (re-calling reuses the running session rather than starting a new one) and mutual-exclusion warnings, but says nothing about what happens if an account is already linked, permission/auth requirements, or how long a QR stays valid. With annotations carrying the safety profile, this is solid but not rich.

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?

Three sentences, each doing distinct work: what it returns, when to prefer it, and the retry/exclusion rules. The core action is front-loaded in the first clause with zero 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?

With no output schema, the description valuably explains the return shape (image, auto-refresh link, data URL) and the expiry/retry loop, which is the main unknown for a pairing tool. The remaining gap is state handling — what to do if the account is already paired or a session is already running outside of restart_session.

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?

Zero parameters, so there is nothing for the description to disambiguate; the 4 baseline applies. The description correctly implies no inputs are needed.

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 ("Initiates pairing and returns a QR code") and enumerates the return payload (image, auto-refreshing link, data URL). It also names the sibling it competes with (request_pairing_code) and why, so the agent can distinguish it without opening a schema.

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?

Gives an explicit preference rule ("Best when the user can scan from another screen"), a retry rule ("If the QR expires, call it again"), and hard exclusions: never combine with request_pairing_code, never call restart_session while pairing. This is exactly the when/when-not/alternatives guidance an agent needs.

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