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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description's only added behavioral value is disclosing that send_email steps return a delivery funnel, which is useful but thin; it says nothing about the shape of 'totals', time-window behavior, or what happens for steps in other states.

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?

A single, front-loaded sentence with zero filler. It is efficient but correspondingly sparse; no clause is wasted, though there is little structure to speak of.

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?

There is no output schema, so the description carries the burden of describing returns; it names 'totals' and the send_email funnel but does not say what totals are included or what non-email steps return. Combined with a fully documented input schema and strong annotations, this is adequate but leaves a real gap for a stats tool.

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 description coverage is 100% — id, step_key, since and until are all documented in the schema itself. The description adds no further semantics for any parameter (e.g., whether since/until are required for funnel data, or expected format for step_key), so baseline 3 applies.

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-plus-resource ('Return totals for one step') and adds scope detail about the delivery funnel for send_email steps. It implicitly contrasts with get-automation-stats (whole automation) via 'one step', but never names that sibling, so distinguishing requires the agent to infer.

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 only implied: 'one step' hints at per-step granularity versus automation-level stats, and the send_email funnel mention hints at when the extra data appears. There is no explicit when-to-use, when-not-to-use, or named alternative (e.g., get-automation-stats).

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