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

The annotations are all false hints and therefore carry no real behavioral signal. The description compensates fully: it discloses write side effects, PDF rendering, idempotency keyed by occurrence date, the 60-invoice run cap, and the created/skipped/still-due return categories.

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 main description is one dense sentence that front-loads the core effect, then states the output categories. Each parameter description earns its place with distinct operational facts; there is no filler or redundancy.

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?

Even without an output schema, the definition tells the agent what side effects to expect, how to preview with dry_run, how many invoices can be created per run, how idempotency works, and what the response reports. That is sufficient to select and invoke it correctly.

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 100%, so the baseline is 3, but the parameter text adds more than a bare schema: as_of includes the dedup key and idempotency, dry_run adds the 60-invoice cap and oldest-period-first ordering, and schedule_id notes free/unlimited scoping.

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 a precise verb and resource: create real invoices for uninvoiced schedule occurrences on or before as_of and render PDFs. The return summary (created/skipped/still due) makes the scope concrete and separates it from read-only schedule tools like schedule_upcoming and forecast.

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 condition is explicit ('occurrences on or before as_of that have not been invoiced yet'), and dry_run plus schedule_id provide clear scoped/test usage. It does not name an alternative or state a when-not-to-use case, but no sibling tool performs invoice generation, so that omission is minor.

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