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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuine value by disclosing the returned shape — all lines, tax breakdown, and post-credit-note balance via credited_minor. It says nothing about behavior for an unknown invoice number (error vs empty result), which is the remaining unknown for an agent.

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?

A single dense sentence with the core action front-loaded and no filler; every clause adds payload information the schema does not carry.

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?

With no output schema and no annotations about return content, the description carries that load and does so well by describing the record's contents. The only gap is missing-invoice behavior and identifier format, minor for a read-only single-entity getter.

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 one parameter with 0% schema description coverage; the description only re-establishes that 'number' is an invoice number. It adds no format, prefix, or example value, so the agent still has to guess the expected identifier syntax.

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 ('Return the full stored record for one invoice number') and enumerates the payload (lines, tax breakdown, open balance), which implicitly separates it from invoice_list. It never names a sibling tool explicitly, so differentiation is inferred 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?

The phrase 'full stored record' hints this is the detail-retrieval path versus a list/summary call, and the mention of credited_minor points to reconciliation use. However, there is no explicit when-to-use, when-not-to-use, or named alternative such as invoice_list or invoice_pdf.

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