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

Annotations only declare readOnlyHint/openWorldHint, and the description adds real behavioral context beyond that: a hard 365-day cap on days, a 500 cap on limit, newest-first ordering, and a workspace-level permission requirement ("Lead-Daten freigeben") that gates the call. It stops short of describing failure modes or what happens when the permission is missing.

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?

Dense and front-loaded with the core purpose, but the inline field enumeration (replied_at, channel, campaign_id, ... step) is largely redundant since an output schema already exists, and the parameter notes are packed into a run-on block rather than structured. Nothing is actively wasteful, but efficiency is only moderate.

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?

Given zero schema descriptions, an existing output schema, and five optional parameters, this covers everything an agent needs: scope, sort order, caps, defaults implied by the bounds, permission prerequisite, workspace ambiguity, and next-step tools. No gap remains that would cause an incorrect invocation.

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 0%, so the description must carry all parameter meaning — and it does: days capped at 365, limit capped at 500, channel restricted to email/linkedin, campaign_id optional with 'all campaigns' as the fallback, and workspace as a slug that may be omitted with a single workspace. Every one of the five parameters gains semantics the bare types do not provide.

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?

Opens with a direct question ("Wer hat geantwortet?") followed by a specific verb+resource: replies of the last N days, newest first, with an enumerated field set. It also names the sibling tools for the natural follow-up actions (lemlist_get_conversation, lemlist_set_lead_interest), so the agent can place it precisely in the lemlist tool family.

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 context and explicit follow-up routing: reply text via lemlist_get_conversation(contact_id), interest setting via lemlist_set_lead_interest. What is missing is an explicit exclusion — it never says when NOT to use this (e.g. use lemlist_list_leads for lead data without replies) or how it differs from lemlist_campaign_performance.

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