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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose real behavior: upsert creates and updates in one call, `list_manage` ADDS by default unless `action="remove"`, `list_export` returns CSV text, and nothing sends email. However, it says nothing about permission/auth requirements, whether `delete` is irreversible, or what the delete/list responses look like — meaningful gaps for a tool with five mutating ops.

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 structure is exemplary for a multi-op tool: a front-loaded conceptual paragraph followed by a compact per-op argument list, so an agent can jump straight to its op. It is dense but almost every line carries information; the one minor inefficiency is the fragmentary trailing ellipsis on the upsert field list, which reads as incomplete rather than concise.

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 an eight-op, 24-parameter tool with no annotations and no output schema, the description covers purpose, op selection, and argument shapes well enough to call it correctly. The remaining gap is return-value behavior beyond the CSV export — list/search response shape and delete confirmation are unstated — which matters somewhat given there is no output schema.

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 only 21% schema description coverage across 24 parameters, the description must compensate, and it largely does: it maps nearly every functional parameter to its op, states the ≤100 cap on `ids_or_emails`, enumerates the filter set, explains `field_rejection_reason`, and lists the upsert identity keys (`contactId`/`email`/`linkedinUrl`) plus editable fields. The meta parameters (`_org`, `_group`, `_project`, `_instance`, `_run_id`) are left to the schema's own descriptions, which is acceptable since those are documented there.

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?

The description names the resource precisely (lemlist CRM contacts plus the lists that group them) and draws the key conceptual boundary: a contact is the campaign-independent PERSON, while its in-campaign copy is a lead, explicitly naming `lemlist_lead`. The clause 'Nothing here sends' immediately tells an agent what class of operation this is not, which separates it from `lemlist_launch_lead` / `lemlist_campaign_start` among the siblings.

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?

The 'Args by op' block effectively documents which op to pick for which need (exact lookup via `ids_or_emails` vs filter-based search, `upsert` as create-AND-update, `list_manage` defaulting to add). It clearly states when to go elsewhere (campaign-lead work belongs to `lemlist_lead`), but it does not explicitly contrast with other contact-adjacent siblings such as `lemlist_create_lead` or `lemlist_get_leads`, leaving that inference to the agent.

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