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

Adds real context beyond annotations: the need for the payments:write scope, the fact that the first call is a pure dry run, that unknown fields are rejected by name, and the exact human-in-the-loop contract before mutation. The gap is the second call's behavior — whether the message is dispatched immediately, whether it can be resent, and what it returns are not stated.

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 purpose, then auth scope, then the numbered two-step protocol, in roughly 50 words with no filler. The short "Two calls." fragment is an effective signpost rather than clutter.

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?

Given two parameters, no output schema, and an openWorld, non-destructive mutation, the description covers the essentials an agent needs to call it safely: auth, the mandatory dry run, and the confirmation gate. The unexplained channel/recipient question and the unstated result of the confirming call are the remaining holes.

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?

confirm_token's role is explained, though the schema description already covers most of it; paylink_id is never described in either place, leaving the description to imply only that it identifies the PayLink. With 50% schema coverage, more was needed — particularly which field (if any) selects email versus text, and the clarification that extra fields are refused despite additionalProperties being true.

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, resource, and delivery channels: "Send a PayLink by email or text." This separates it cleanly from create_paylink, cancel_paylink, get_paylink, and list_paylinks without needing to name them.

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?

It gives unusually concrete when-to-use guidance in the form of the required two-call flow: first a no-op validation call, then a repeat call with confirm_token only after the person agrees. What's missing is routing versus alternatives — it never says to use create_paylink first or to prefer send_message for plain outreach.

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