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

Adds substantial context beyond destructiveHint=true: which systems are mutated (Telegram session, macOS Keychain, LMCP account list) and the crucial reassurance that chat history remains in Telegram. This directly answers the questions a destructive tool raises for an agent before invoking it.

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?

Effect is front-loaded in the first sentence, with the account-selection rule last where it matters for invocation. The dense semicolon chain is efficient, though slightly compressed for the amount of state-change information packed into it.

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?

Output schema covers return values and annotations cover the safety profile, so the remaining burden is explaining scope of destruction and account selection — both are addressed. Nothing an agent needs to call this correctly is missing.

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 schema already documents both properties, including the conditional-required rule for `account` and that `confirm` is ignored. The description's clause about omitting `account` largely restates the schema, so it meets but does not exceed the baseline.

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?

Specific verb+resource ('Disconnects a Telegram account from LMCP') followed by the exact side effects (Telegram-side sign-out, Keychain removal, removal from LMCP account list). It is unambiguously distinct from telegram_connect and from the disconnect tools for other services in the sibling list.

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 a clear operating condition for the `account` selector ('with one account it can be omitted, with several it must be given') and points at telegram_list_accounts via the schema as the source of labels/ids. It does not state explicit when-not-to-use or warn that this is irreversible, so it falls short of 5.

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