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

Annotations already disclose destructiveHint=true and idempotentHint=false, so the bar is lower; the description still adds real context by stating that deleting an item does not remove lines already on invoices, and that save without id creates versus with id edits. It does not say whether edits are reversible, what happens to items referenced by templates, or anything about permissions.

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 sentence leads with the resource then breaks each action into a parenthetical clause — front-loaded and essentially waste-free. The telegraphic compression makes it dense to parse on first read, which keeps it just under 5.

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 9-parameter, nested-object mutation tool with no output schema, the description covers the action semantics and delete side effects but omits what list returns (item shape, currency interpolation), how defaults like baseCurrency apply across actions, and the non-idempotency implication of save. Adequate to invoke, incomplete for confident use.

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 78%, so the schema already documents id, name, prices, unitPrice, baseCurrency and defaultTaxRate. The description only restates that prices are decimal strings and that save needs an id to edit, adding little beyond the structured fields; it says nothing about the nested prices object's conversion semantics or the relationship between unitPrice and prices.

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 the resource precisely ("saved invoice items (services / products)") and enumerates the three supported actions with their effect, which lets an agent separate it from invoices_manage or invoice_payments_manage. It stops short of explicitly stating the boundary against those siblings.

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?

Each action carries its use condition: list returns prices per currency, save is create-or-edit-by-id, delete removes the item but leaves existing invoice lines intact. No exclusions or named alternatives (e.g., editing a line on an existing invoice via invoices_manage) are given, which keeps it a step below 5.

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