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

Annotations only declare readOnlyHint=false and destructiveHint=false, yet the description adds substantial behavior: losing sibling channels are cancelled, exactly one proof is billed at the winning channel and nothing at creation, and the tool requires an authenticated Proof account (start_login does not unlock it). These are non-obvious side effects and prerequisites an agent cannot get from the schema.

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?

Dense but front-loaded: the first sentence nails the core mechanic, the billing constraint follows, then agent usage and the rendering caveat. Every sentence carries operational information, though the block is long enough that a reader must work through three paragraphs to reach the polling instruction.

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?

Despite having no output schema, the description fully documents the return shape (group_id, channels array with deep_link/sms_message/qr_text), the follow-up polling tool, the billing model, and the auth prerequisite. Nothing needed to invoke and correctly handle this tool 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%, so the baseline is 3, but the description adds real meaning beyond it: it explains the first-wins semantics of the channels array and documents the response shape (group_id vg_<hex>, per-channel deep_link vs sms_message, and qr_text as pre-rendered art rather than an alternate address).

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 ('Create a multi-channel phone verification') and immediately defines the mechanism: one number challenged over several channels with OR / first-wins semantics. This distinguishes it from the single-channel create_verification / start_add_phone siblings without the agent needing to open either 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 concrete follow-up routing: pass deep_link to render_auth_link, poll get_multi_channel_verification_status with the group_id, and an explicit caveat about not relying on tool-result rendering. It never explicitly states when to prefer this over create_verification (single channel), so it stops just short of a full when/when-not treatment.

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