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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely new behavior: the invoice is a frozen snapshot 'as issued' rather than a recomputation, and logos are deliberately omitted from the result.

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 economical sentences, front-loaded with what the resource is and what it contains, then the one optional flag, then a deliberate omission. 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?

An output schema exists so return values need no explanation, and the description covers content and the detail flag. Minor gap: no mention of error behavior for an unknown/nonexistent invoice id.

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 100%, so the baseline is 3, but the description adds meaning by describing the output shape in each parameter state: default returns lines per project and totals, while include_detail expands to a per-entry breakdown.

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 implicitly (retrieving the frozen invoice) and enumerates its content (seller, client, lines per project, totals). This clearly separates it from list_invoices, create_invoice, and mark_invoice_paid in the sibling set.

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?

Usage is implied: fetch one already-issued invoice by id. There is no explicit when-to-use vs. list_invoices (to find an id) or create_invoice, and no note about whether drafts or unpaid invoices can be retrieved.

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