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

Adds substantial context beyond the annotations: the object is created as a draft and sends nothing, campaigns cannot be deleted through the API (making validate_only the safety valve), and stop_on_email_replied is written but not readable back (not_readable). This is exactly the kind of operational caveat the readOnly/destructive hints cannot convey.

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, then organized by parameter/caveat with labels ('steps:', 'sender_user_ids:', 'Rückgabe:'). Dense but every block carries unique information; the only minor waste is restating return values that the output schema already provides.

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 7-parameter, nested-array creation tool this covers nearly everything an agent needs: step schema, sender prerequisite, validation workflow, non-deletability, and return shape. Remaining gaps are minor (timezone default behavior, rate limits) and the output schema already covers returns.

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 0%, so the description must carry the load, and it does: it documents the nested steps item shape (types email/linkedinInvite/linkedinSend/linkedinVisit/manual/phone, per-type fields, 300-char limit, delay semantics, plaintext vs HTML, placeholder preservation, max 20 steps), plus sender_user_ids, stop_on_email_replied and workspace. Only timezone (and the trivial name) is left undocumented.

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 ('Neue lemlist-Kampagne mit Sequenz anlegen') and immediately clarifies the resulting state (draft, sends nothing until started). It also names the sibling that advances the lifecycle (lemlist_start_campaign), so the agent can distinguish create from start without opening a 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?

Gives clear preconditions and workflow: senders from lemlist_mailbox_health are required or the campaign cannot start, and validate_only=True should be used first because campaigns cannot be deleted via the API. It does not, however, distinguish this from lemlist_update_campaign or explain when to prefer adding steps to an existing sequence.

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