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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the link is 'private' (access-controlled) and the original may be an email, PDF or scan, so the returned artifact varies in format. It does not say whether the link expires or what happens when no original exists.

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 short, front-loaded phrase with no filler. The only weakness is that it is a noun phrase rather than a statement of action, which makes the sentence slightly less immediately actionable.

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 simple single-parameter read tool with full annotation coverage, the description covers what is returned and that it is private. However, with no output schema, gaps remain around link lifetime, availability when no original exists, and the invoice_id format, which the description should have supplied.

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?

There is a single required parameter (invoice_id) with 0% schema description coverage, so the description must carry the burden. 'One invoice' implies the parameter identifies exactly one invoice, but nothing explains the ID format, where to obtain it, or what happens with an unknown ID.

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?

The description names a specific resource and scope: a link to the original email, PDF or scan of exactly one invoice. The verb is implicit (the name get_original plus 'a private link to...' makes retrieval clear), and 'one invoice' distinguishes it from list-style siblings like list_invoices, though no sibling is named 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?

There is no explicit when-to-use or when-not-to-use guidance and no alternative tool is referenced. The trailing clause 'to show the trade' hints at a use case (presenting proof of an invoice to a counterparty) but is too terse to count as real guidance.

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