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

Adds a great deal beyond the annotations: authorization requirements (owner or admin of both the source and target workspace), handle lifetime (15 minutes), single-use semantics ('spent by the first run that succeeds'), and the webhook precondition that a bot connected elsewhere is refused. The expiry/single-use nature of the handle is exactly the kind of 'what gets destroyed' context annotations cannot convey; the single-use handle creates mild tension with idempotentHint=true but does not contradict it, since the call itself persists no state.

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?

Front-loaded with the core promise ('WITHOUT seeing it') before any detail, then cleanly segmented into example usage, a 'source, exactly one of:' list, and a 'Rules:' block. The usage paragraph is dense with two full call signatures and could have been tightened, but every sentence carries operational information.

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?

There is no output schema, and the description supplies the return contract itself (the `clip:<id>` handle, and for identities the accompanying origin/username). Combined with auth, expiry, and cross-workspace constraints, an agent has everything needed to call it correctly and to know what it will get back.

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 is 3, but the schema only describes `source` as a one-line union while the description spells out each variant's shape, the default `pattern` value, and where the ids come from (messages.read_history, browser.list_identities). It also clarifies that a password handle is bound to its recorded origin; only `in_workspace` is left to the schema.

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 object ('Copy a secret ... WITHOUT seeing it') plus the distinctive scope: the value is never returned, only a `clip:<id>` handle. The contrast with ordinary read tools is explicit, so an agent can tell this apart from anything that would expose the secret directly.

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?

Names the exact consumption points with concrete signatures (channels.connect_telegram_bot, browser.create_identity) and states the negative rule: 'any other parameter refuses a handle.' The three `source` variants are enumerated as a choice with the condition that selects each (message pattern default, connected bot, identity password), so there is nothing left to infer.

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