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

Annotations already declare write, destructive and idempotent behavior, so the description correctly focuses on what annotations cannot express: the draft-only precondition, the non-DST fixed-offset timezone trap and how to mitigate it, and the undo window. It does not state what the campaign's resulting state is or how the tool behaves if the campaign is already scheduled or already sending.

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 tightly packed sentences, front-loaded with the write/deferred framing before the mechanics and the undo path. The trailing HTTP route is marginal value for an agent but costs little; the capitalized lead-in is slightly shouty without being wasteful.

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 3-required-param mutation with no output schema and full annotation coverage, the description covers the two things most likely to cause a bad call: scheduling a non-draft and picking a wrong timezone id. It omits what the call returns and how repeat/already-scheduled calls behave.

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% and all three parameters are documented in the schema, which sets the baseline at 3. The description does add genuine semantics for timezone_id (fixed-offset, no DST, must match the send date's offset) rather than repeating the schema, but scheduled_time's format is left entirely to the schema.

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 ('schedule a DRAFT campaign') and adds the precondition that matters (must be a draft) plus scope ('all its recipients'). The 'SENDS EMAIL TO CUSTOMERS LATER' framing separates it cleanly from emailchef_send_campaign and emailchef_send_test_campaign without needing 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?

Gives explicit when-to-use context (deferred send of a draft), names the prerequisite lookup tool emailchef_list_timezones, and names the reversal path emailchef_unschedule_campaign before the send starts. It stops short of explicitly contrasting with emailchef_send_campaign, leaving the send-now vs send-later choice to be inferred from 'LATER'.

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