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

Annotations already cover read-only behavior, and an output schema exists. The conditional note that ab_variants is only present when the campaign A/B tests adds genuine behavioral insight, but most of the rest of the description restates return fields that the output schema already enumerates. Coverage is adequate but not rich beyond 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?

The description is front-loaded with the core purpose and reasonably structured, but the long enumeration of returned fields (invited, sent, delivered, ...) is verbose and largely duplicates the output schema, adding some redundancy.

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?

With an output schema present, the tool doesn't need to explain return values, yet it provides enough context about purpose, alternative tools, and date/workspace semantics that an agent can call it correctly. Missing details on campaign_id and channel are minor gaps covered by the cross-reference.

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?

With 0% schema description coverage, the description compensates partially: it documents workspace as a customer-workspace slug (optional with a single workspace) and date strings as YYYY-MM-DD (UTC), and explains days vs. date_from/date_to. However, campaign_id and channel are only weakly covered ('wie dort'), leaving meaning to be inferred from the sibling tool.

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 scope: metrics (Kennzahlen) of a lemlist campaign broken down by sequence step and A/B variant. This clearly distinguishes it from lemlist_campaign_performance (campaign total) and lemlist_get_sequence (step text).

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?

Routes the agent to alternatives by cross-referencing lemlist_get_sequence for step texts and lemlist_campaign_performance for the campaign-level total. The implicit guidance is clear even though it doesn't explicitly say 'use when...' for a step-level breakdown.

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