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

Annotations declare destructiveHint=true and idempotentHint=false, but the description adds value beyond them: it discloses that this is a 'confirmed, two-step action' requiring explicit user agreement, and spells out the preview-first workflow. It does not state idempotency or what happens on repeat calls, but the two-step confirmation protocol is a real behavioral disclosure the annotations don't provide.

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 the core action, then the confirmation protocol. Two paragraphs, each earning its place. Slightly verbose on the bulk case but well-structured and not padded.

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?

Given a mutation tool with destructive annotations and an output schema (so return values needn't be explained), the description covers the critical workflow: preview, confirm, bulk handling. Missing explicit mention of reversibility or what happens when the invoice isn't found, but otherwise complete for safe invocation.

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%, with each parameter already documented (on, amount, vendor, confirmed, invoiceNumber). The description reinforces the semantics of `confirmed` through the workflow narrative but adds no syntax or format details beyond what the schema provides. Baseline 3 is appropriate.

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 (mark paid) and resource (a specific invoice in the user's own Xenition ledger), scoping it to the user's ledger. Clear enough that an agent can distinguish it from query_ledger and add_ledger_entry.

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?

Explicitly prescribes the when: first call without `confirmed` to preview, relay to user, then call again with `confirmed:true` after explicit agreement. Also covers the bulk case (mark ALL/EVERY invoices) with its own confirmation path. Nothing left to inference.

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