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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the mutation profile is covered structurally. The description adds genuinely useful context that the notices are session-scoped ('for this session'), which the annotations cannot convey. But its claim that omitting the account removes watches 'for every account' is a behavioral assertion that conflicts with the parameter documentation stating the omission uses the default account.

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 well-formed sentence with the action front-loaded and the scope qualifier trailing it. There is no filler or restatement of the tool name beyond what clarity requires.

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 optional parameter, the description states the action, its relationship to the sibling that created the state, and that the effect is session-scoped; an output schema exists so return values need no explanation. The only gap is the inconsistent omission semantics, which is scored under parameter semantics rather than double-counted here.

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%, so the baseline would be 3, but the description actively contradicts the schema here: it says the watch is stopped for every account when `account` is omitted, while the schema says the omission means the default account. That contradiction is worse than adding nothing, because an agent relying on the prose would silently unwatch all accounts.

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?

Names a specific verb and resource ('Stops the Telegram message notices') and ties itself directly to the sibling telegram_watch_chats, so an agent can tell it is the inverse of the watch tool. The scope clause is however factually at odds with the schema, which slightly muddies what the tool actually does when no account is given.

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 only implied through the counterpart reference — an agent can infer to call this when it no longer wants the notices telegram_watch_chats created. There is no explicit when-to-use/when-not statement, and telegram_watch_status is never mentioned as a way to check whether a watch exists before unwatching.

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