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

Annotations cover the safety profile (readOnlyHint=false, openWorldHint=true, destructiveHint=false). The description adds genuinely new context the annotations don't: it enumerates the returned fields (authorize_url, connect_id, expires) and warns against auto-polling, hinting at a session/expiry lifecycle. It still doesn't state auth prerequisites or what expiration actually means in practice.

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 short, front-loaded sentences that each carry information — action, constraint, return contract, and caution. The only waste is the vague 'Tri-channel alias' opener and 'expires guidance', which is imprecise phrasing for a return value.

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 and 0% schema coverage, the description must compensate, and it does name the return fields and delegation target. But it omits the purpose/format of connection_context and gives no indication of when the session must be consumed before it expires, leaving an agent unable to call this fully informed.

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 0%, so the description carries the burden. It usefully supplies the missing constraint that 'channel' must be 'tiktok' (the schema has no enum or description), which is real added value. However, connection_context is never mentioned, despite its strict mctx_v1_ pattern, so half the parameters remain opaque.

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 action (begin a browser channel connection) and resource, and names the delegate tool tiktok_begin_auth_onboarding, which helps distinguish it from siblings. The 'Tri-channel alias for TikTok connect' framing is confusing, since the next sentence says channel must be 'tiktok' — it implies a multi-channel capability that doesn't exist.

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 one hard constraint ('channel' must be 'tiktok') and one behavioral instruction ('Do NOT poll automatically'), which implies polling belongs elsewhere. It never names setup_check_channel_connect or explains when to prefer this over calling tiktok_begin_auth_onboarding directly, so the routing decision is left to inference.

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