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

No annotations are supplied, so the description carries the full burden. It does disclose one meaningful behavioral fact — credits are what enrichment spends — and establishes that these are lookup operations keyed off an `op`. However, it says nothing about authentication, rate limits, failure modes, or whether operations mutate anything, which matters for a tool with 12 parameters including run/scope identifiers. Adequate but with clear gaps against a zero-annotation baseline.

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 two-sentence header front-loads what the tool is and why it matters before the per-op breakdown, and the bulleted 'Args by op' structure is easy to scan and mirrors the op enum. Each bullet earns its place by naming the relevant arguments and their valid values. Slight verbosity in parenthetical asides keeps it from a 5.

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-operation tool with 12 parameters, no annotations, and no output schema, the description covers what an agent needs to select the right `op` and pass the right argument. It even sketches return content per op (members and their campaigns, the user's mailboxes and LinkedIn/WhatsApp accounts). It does not describe response shapes or pagination, which matters precisely because no output schema exists.

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 only 42%, so the description must compensate, and it does for the business-relevant parameters: it decodes `state` as campaign status, `crm` as hubspot/salesforce, `filter_type` as lead/contact/report, `entity` as contact/company, and `source` as default/custom/crm_synced — none of which the schema states. It also maps each parameter to its owning `op`, which is essential for a multi-op tool. The infrastructure parameters (_org, _group, _project, _instance, _run_id) are left entirely to the schema, preventing a 5.

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 first line names the resource precisely — the Lemlist workspace — and enumerates the eight entities it can return (team, credits, senders, users, CRM link, fields), which is enough for an agent to distinguish it from list/entity tools like lemlist_campaign or lemlist_lead. The second line ('Where the ids other tools ask for come from') adds a genuine role statement. It lacks a single unifying verb, but the op enum plus the enumeration makes the purpose unambiguous.

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 spelled out per operation, including cross-tool routing: `user_channels` is explicitly the source of the ids `lemlist_inbox_send` requires, and `crm_filters` is explicitly the selection `lemlist_lead(op="import_crm")` consumes. That is real when-to-use guidance tied to siblings. It stops short of exclusions — it never says when NOT to use this tool versus siblings such as lemlist_status or lemlist_mailbox — so it is not a 5.

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