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

Goes well beyond the annotations: numbering is gapless and therefore one-way, legal validation can refuse (free) or warn, e_invoice adds Factur-X/XRechnung validated against the official schema, cost is $0.10 per call and nothing on failure, and posting to books happens when books_setup is active. The irreversibility and the validate-before-number ordering are exactly the operational facts an agent needs and cannot get from readOnlyHint/destructiveHint alone.

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 action is front-loaded in the first sentence and nearly every clause carries distinct information (numbering, PDF, email, validation, e-invoicing, pricing). It is delivered as one dense block with parenthetical sub-clauses, which slows parsing of the legal-check section, but there is little genuine waste to cut.

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 mutating, open-world tool with no output schema and only generic annotations, the description covers the full lifecycle: numbering, PDF persistence, delivery channels, legal gating, e-invoice output, bookkeeping side effect, and billing. It omits what the call returns (document id/URL) and any rate-limit or retry guidance, which are the remaining gaps an agent might want.

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 baseline is 3, but the description earns a bump by explaining the non-obvious semantics: email:false means 'number it and hand the link over yourself' and `to` only overrides on resend ('to `to`, if given'). `message`, `link_hours`, and `invoice_id` are left entirely to the schema, which is acceptable at this coverage level.

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 and resource ('Send a draft') and enumerates the concrete side effects: gapless numbering, PDF generation into the file store, and customer email with page and PDF links. It also covers the resend case and the email:false variant, so an agent can tell this apart from invoices_create, invoices_update, and invoices_remind without opening their schemas.

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 clearly frames the two entry conditions: a draft (numbers, renders, emails) versus an already-sent document (re-emails to `to` if given), plus the manual-delivery path via email:false. It stops short of explicit exclusions, though – it never says to use invoices_convert_quote for a quote→invoice path or invoices_void/remind instead, leaving the agent to infer those boundaries from sibling names.

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