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

Annotations already declare the full safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false), so the description's marginal burden is low. It still adds real context beyond the annotations: the capability boundary that Xenition has no payment or messaging channel, which prevents an agent from attempting a send. It does not address duplicate-entry behavior on repeat calls, though idempotentHint=false already signals that.

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?

Two sentences, zero waste. The positive trigger and the field summary come first, and the exclusion is placed last where it functions as a guard rather than burying the primary purpose.

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 mutation tool with full annotation coverage, a rich schema and an output schema, the description supplies what structured data cannot: the use trigger and the capability boundary. The only unaddressed point is duplicate handling on repeated calls, which is a minor omission given idempotentHint=false.

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 86%, so the schema already documents kind, amount, vendor, dueDate, currency, markPaid and invoiceNumber. The description's 'optionally already paid' is a useful gloss on markPaid, but it adds no syntax, format, or default details beyond what the schema states. Baseline 3 is appropriate when the schema carries the load.

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 (record) plus the resource (invoice/bill/receipt in the Xenition ledger) and enumerates the key fields (vendor, amount, due date, paid state). It also explicitly carves out the adjacent-but-different operations (pay, send, email), which lets an agent separate this from siblings like mark_paid without opening either schema.

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 trigger is explicit ('Use this when the user wants to record an invoice, bill or receipt'), and it adds a genuine exclusion ('Do not use to pay, send or email an invoice'). What it lacks is a named alternative — mark_paid and query_ledger are never referenced by name, so the routing is implied rather than spelled out.

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