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

Goes well beyond the annotations: booking is irreversible (a booked invoice cannot be edited), sending is conditional on booking success, EAN has master-data prerequisites, there is a default per-call confirmation that can be toggled, the action reaches third parties requiring user confirmation, and a specific API key scope is required. This is exactly the mutation/irreversibility context annotations do not supply.

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 and its effects, then prerequisites and confirmation behavior. Slightly repetitive around confirmation ('confirm each call' / 'confirm with the user before each call'), but nearly every sentence carries actionable detail.

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 non-read-only, open-world mutation with no output schema, the description covers irreversibility, side effects, prerequisite data, auth key requirements, and confirmation policy. Nothing an agent needs to call it safely is missing.

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% (baseline 3), and the description adds consequence-level meaning for send_by (email/ean triggers sending only after successful booking; EAN has data prerequisites). book_with_number semantics are left entirely to the schema, so it is above baseline but not exhaustive.

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 (book) and resource (draft invoice) and clearly delineates it from create_draft_invoice/list_draft_invoices by explaining that booking assigns an invoice number and finalizes the draft. An agent can distinguish this from sibling invoice tools without opening any 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?

Gives clear conditional guidance: send_by email/ean sends after a successful booking, otherwise nothing is sent, and EAN requires CVR/country in master data plus a recipient identifier. It does not name the sibling tools that produce a draft, but the when-to-send decision logic is explicit.

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