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

Annotations cover safety (readOnly=false, destructive=false, idempotent=true), but the description adds genuinely non-structured behavior: start runs validation over sender, trigger and every email and reports what to fix, pause leaves contacts paused in place rather than removing them, and the tool needs the Publish scope. That is exactly the kind of pre-flight and side-effect detail annotations cannot express. Missing only error/return shape, which is minor.

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 three actions, then the validation behavior, then the confirmation rule and scope requirement – a sensible order with no filler. The prose is slightly telegraphic ('resume goes on'), but every sentence carries information.

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 two-parameter mutation with no output schema, it covers the action semantics, the pre-flight validation and its reporting, the confirmation requirement, and the auth scope. An agent could call it correctly and safely from this alone; only the failure/return behavior is left implicit.

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 50% – automationId is documented there, but the action enum values are not. The description compensates by explaining what each of start/pause/resume actually does to the automation's state and to contacts in flight, which the raw enum does not convey.

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 the specific resource (an email automation) and the three state transitions it performs, and the first three clauses map one-to-one onto the action enum. It stops short of naming how it differs from nearby siblings like postfjord_set_automation or postfjord_create_email_automation, so an agent must infer the boundary.

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 concrete when-to-use semantics per action ('start turns a draft on', 'pause stops sending', 'resume goes on') plus a real procedural constraint: confirm with the person before start or resume. No explicit when-not-to-use or routing to an alternative tool, which keeps it below a 5.

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