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

Annotations already declare destructiveHint, idempotentHint and openWorldHint, so the bar is lower, yet the description adds real context: retry safety via intent reuse, reconciliation on ambiguous provider responses, the external Square dependency, and the money boundary (no refunds, no fund movement). What's missing is what a confirmed cancellation actually returns or what failure states look like.

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 dense sentences, each carrying a distinct load: identity, retry/reconciliation behavior, and financial scope. The core action is front-loaded and there is no filler.

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 destructive, idempotent, one-param mutation tool with full annotation coverage and no output schema, the description covers safety, retry semantics, and side effects on money. The residual gap is the intent parameter's provenance/format, which is the one thing an agent must get right to call it.

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% — `intent` is only typed as a 1-200 char string. The description partially compensates by framing intent as a stable handle for a prepared cancellation whose reuse polls status instead of re-sending, which is meaningful semantics. It still never states where the agent obtains the intent value or what form it takes.

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 ("Confirm one prepared Square cancellation") and narrows scope with "one" and "prepared", which implicitly points at the prepare/confirm two-step pattern. It stops short of naming prepare_booking_cancellation explicitly, so the sibling differentiation is inferable rather than stated.

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 operating guidance: an ambiguous provider result means reconcile rather than retry a new cancellation, and repeating the same intent is the way to poll status. It does not explicitly say 'call prepare_booking_cancellation first' or name the alternative tool, but the when-to-call context is clear.

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