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

Annotations already declare destructiveHint=true and non-idempotent, but the description adds real context beyond that: what gets changed (financial records), the exact two-step confirmation protocol, the preview-then-commit sequence, and the required user agreement before any write. This is meaningful behavioral disclosure, not restatement.

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?

Front-loaded with purpose and effect, then the confirmation flow, then the bulk caveat. Every sentence carries a distinct instruction with no filler, despite being longer than typical.

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 needn't be detailed, and the description still notes it returns the ledger's invoices. For a destructive, multi-parameter mutation, the confirmation protocol, bulk handling, and scope are all covered.

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 schema already documents all five parameters (baseline 3). The description goes further by explaining the operational role of `confirmed` as a gate that produces a preview on the first call, which adds workflow meaning beyond the field description alone.

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: 'Mark a specific invoice in the user's own Xenition ledger as paid.' The scope ('specific invoice', 'user's own ledger') is clear. It doesn't explicitly name the read-side sibling (query_ledger), so differentiation from alternatives is implicit 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?

Explicit and prescriptive: call without `confirmed` first to preview, relay to the user, then call with `confirmed:true` only after agreement. It also handles the bulk case (ALL/EVERY/multiple) with its own confirmation protocol. Nothing is left to inference.

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