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

Annotations only indicate non-read-only and non-destructive; the description adds the useful caveat that a generic insert does not perform invoice side effects. It does not go further into validation, ID generation, or returned values, so it provides moderate but not rich behavioral context.

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?

The description is front-loaded: action and key caveat first, alternative second, resource enumeration last. The resource list is redundant with the schema enum but convenient; otherwise no sentence is wasted.

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 generic multi-resource create with no output schema, the description is nearly complete: it names all creatable resources, excludes invoices explicitly, and warns about absent invoicing side effects. It stops short of resource-specific data shape guidance or post-create behavior, but those may be intentionally delegated to per-resource catalogs.

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?

With 50% schema coverage, the description repeats the resource enum in plain language and adds examples, but it does not explain per-resource field requirements for `data` beyond 'The record's fields.' The invoice exclusion is a meaningful semantic distinction for `resource`, but the description still relies on the schema for most parameter meaning.

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 first sentence names the action (create) and the affected resources (customer, product, vendor, employee, asset, or other simple record), and the second explicitly carves out invoices with fawtar_create_invoice. This makes the tool's scope concrete and distinguishes it from its nearest sibling.

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?

It states the key alternative, fawtar_create_invoice, and the condition for choosing it ('for invoices'), with concrete reasons (sequential number, VAT, QR, ledger posting). This is exactly the when-to-use vs when-not-to-use guidance an agent needs.

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