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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=true, so the warning profile is covered structurally. The description adds genuinely useful non-derived context: the payload must match exactly what was prepared and the confirmation token is single-use and validated. It omits what actually happens after sending (invoice issuance to the customer, irreversibility, token-expiry or duplicate-token failure modes), which for a destructive open-world action is the most valuable missing detail.

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?

One tightly written sentence, front-loaded with the action and immediately qualified by the preconditions. Nothing is redundant, though the sparseness leaves room that could have been used for idempotency semantics at no cost to clarity.

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?

An output schema exists, so return values need not be explained, and the annotations cover the safety profile. However, for a destructive, open-world, three-required-parameter send with zero schema descriptions, the definition is thin: idempotency behavior, prerequisite ordering, and post-send state are all unaddressed.

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 description coverage is 0% for three required parameters, so the description must carry the burden. It only illuminates 'confirmationToken' (one-use, validated); 'invoiceId' and especially 'idempotencyKey'—whose retry-safety contract is critical for a send operation—are left completely unexplained.

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 concrete verb and resource ('Sends ... invoice') and pins down the payload as 'the exact prepared invoice payload', which implicitly distinguishes this from prepare_invoice_send. It stops short of naming the sibling, so an agent must infer the two-phase relationship from 'prepared' rather than being told explicitly.

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?

'after validating the one-use confirmation token' implies a prerequisite prepare step exists, but no sibling is named and there is no statement of when not to call this (e.g., use prepare_invoice_send first). Usage is implied rather than spelled out.

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