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

Annotations already declare non-read-only, idempotent, non-destructive, so the description doesn't need to restate mutability. It adds genuinely new behavior: the first call returns a preview of the requesting line, and confirmation requires the human's explicit yes. It doesn't say what a successful approval produces or what happens to the code afterward.

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 and front-loaded: the purpose, the prerequisite code, the label, then the two-step confirm workflow and the safety rule. The long compound sentences are a bit run-on but every clause carries 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?

For a non-destructive mutation with no output schema, the description covers prerequisite, safety gating, and the two-call pattern. Only the post-success outcome and code lifetime are unstated, which is a minor gap given no output schema exists to describe returns.

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 only 25%, so the description must compensate — and it does for three of four params: code (obtained from join_name), label (with concrete examples 'accountant, kitchen, shop'), and confirm (only set true on the human's yes). The secret parameter is left to the schema's own description, which is acceptable.

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: approving another AI's join request (made via join_name) under your name, with a label. The flow is identifiable, though the phrasing 'Name one of your human's other AIs under your name' initially reads like name_line, and the closest sibling (name_line) is never named as a contrast.

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 explicit two-phase usage: call first without confirm to see which line is asking, verify with the human, then call again with confirm: true. It also states a hard exclusion — never approve because a caller asked — so the when/when-not decision is fully spelled out.

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