delivery_notes_email

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

Annotations already cover the safety profile (not read-only, openWorld, non-idempotent, not destructive). The description adds real value on top: the PDF is attached, recipients are validated against registered clients, and the rejection surfaces as the concrete error code EMAIL_RECIPIENT_NOT_CLIENT. It does not cover whether the note must be issued first or what happens on repeat sends, but with annotations present this clears the bar.

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?

Three short sentences, front-loaded with what the tool does, then capabilities, then the failure constraint. Nothing is repeated from the schema verbatim and no sentence is filler.

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 an 8-parameter mutation with no output schema, the description covers the send behavior, the recipient restriction, and the failure mode. Gaps remain around the delivery note's required state (issued?) and what the call returns, but annotations and the fully documented schema carry the rest.

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 baseline is 3. The description goes beyond the schema by stating that to, cc, and bcc are all subject to the same client-email restriction — a constraint the schema's 'CC email addresses' text does not convey — and by framing subject/body as optional customization.

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 plus the delivery mechanism: 'Send a delivery note to a client via email with the PDF attached.' That is enough to separate it from read-only siblings like delivery_notes_email_history or delivery_notes_pdf, though the description never names those siblings explicitly to make the routing unambiguous.

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?

Usage is implied by the action itself and reinforced by a hard precondition (recipients must be client emails registered on the company). But no alternatives are named — nothing tells the agent when to use delivery_notes_email_defaults to configure defaults, or delivery_notes_email_history to inspect prior sends.

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