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

Annotations only declare the generic write profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds the substantive behavior: nothing is sent until switched on, calls without segment_id for audience_entered/exited are refused, max 5 emails, delays are relative to the previous step, and copy must be authored by the agent. These are non-obvious operational facts an agent cannot infer from 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?

Front-loaded with purpose and the concrete example, and every clause carries a real constraint. It is a single dense paragraph with stacked parentheticals and em-dashes, which slightly hampers scanning but wastes no sentences.

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?

Covers the mutation's safety profile, constraints, and follow-up routing well for a 6-param write tool with no output schema. The only gap is that it never says what the call returns (a journey id?), which would help the agent chain into get_journey or set_journey_enabled.

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 nonetheless adds the refusal semantics for segment_id and the scope of trigger_event (audience_entered as "the usual welcome/nurture"). It doesn't add format-level detail beyond the schema (e.g. body_html size limits), so it sits just above baseline.

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 ("Save a DRAFT automation journey") plus the model it creates: trigger event, then ordered waits and emails, illustrated with a concrete VIP-segment example. This cleanly separates it from set_journey_enabled, add_journey_step, and draft_campaign without needing the 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?

Explicitly says the journey is saved switched OFF and that enabling happens in the editor or via set_journey_enabled "only when the user asks" — a direct when/when-not rule with a named alternative. It also routes segment lookups to list_contact_filter_vocabulary / create_contact_segment and defers branches to the editor, so the agent knows what not to attempt here.

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