beel_create_invoice_delivery

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

Annotations already signal mutability (readOnlyHint=false), and the description adds valuable behavioral context: it states that partially failing PDF attachments are reported in `failures` and the email is still sent for the rest. It also clarifies that no recipient is inferred from profiles. This goes beyond the annotation hints and aids the agent in anticipating partial failures. No contradiction with annotations.

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 description is two sentences (plus an endpoint line) with no redundancy. The primary action is front-loaded, and the constraint and failure handling are conveyed in a compact, structured way. Every sentence earns its place without padding.

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 tool that sends email deliveries, the description covers the key behavioral aspects: the purpose, the limit, the requirement for recipients, and the failure reporting. It also includes the endpoint for debugging. However, it does not describe the response structure beyond `failures`, which is somewhat important given there is no output schema. This leaves minor ambiguity about what else the response contains, but the core use case is clear.

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 67% (most parameters have descriptions). The description adds a bit of meaning by implying invoice_ids are invoices whose PDFs are attached and by restating the recipient requirement, but these align with schema constraints (maxItems=200, minItems=1). The idempotency_key behavior is described in the schema, not the tool description. The description compensates only slightly for the coverage gap, so a 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?

The description states a specific action ('Sends one email carrying the PDFs of up to 200 invoices of this company as attachments'), a clear resource (invoices of the company), and scope (up to 200). It distinguishes itself from siblings like beel_send_invoice (single invoice) and beel_get_email_delivery (retrieval) by describing the multi-invoice email delivery behavior.

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 description implies when to use the tool (to send multiple invoices by email) and provides a strict requirement (at least one recipient, no profile inference). However, it does not explicitly contrast with alternatives or state when not to use it (e.g., for a single invoice use beel_send_invoice). The context is clear but lacking explicit exclusions or alternative routing.

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