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

With all annotations false, the description carries the full disclosure burden. It reveals non-obvious behaviors: privacy-blocked members appear in a failed list, the slug allows later addressing without a JID, and the tool falls back to the org's default session unless channelId is provided. It could also mention return structure or permission requirements, but the disclosed behaviors are substantive and go well beyond a generic creation statement.

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?

Four dense sentences with zero filler. The first sentence identifies the verb and resource, then each subsequent sentence adds a distinct behavioral fact: member-source combinations, slug addressing, privacy-failure handling, and session selection. For a 12-parameter creation tool, this is appropriately sized and well front-loaded.

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?

The description covers the core creation action, all major input source categories, slug semantics, a partial-failure mode, and session selection — a strong picture for a complex tool with no output schema and no annotations. The main gap is that it doesn't describe what a successful response contains (e.g., group ID/JID), though the mention of a 'failed list' hints at the response shape. This is a minor omission given how much else is covered.

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 100%, so the baseline is 3. The description adds conceptual grouping that the flat schema doesn't: it explains that member sources can be combined from groups (fromGroupIds), contact lists (listIds), individual contacts (contactIds), pasted numbers (phones), or the whole address book (allContacts). It also clarifies the slug's purpose ('address the group later without its JID'), which goes slightly beyond the schema's own description.

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 opens with a precise verb and resource: 'Create a new WhatsApp group.' It then adds the member-seeding scope and the slug mechanism, making it clearly distinct from siblings like neuron_add_group_members, neuron_update_group_settings, and neuron_remove_group_members. The word 'new' also signals the lifecycle stage, so an agent immediately knows this is for group creation, not modification.

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 description makes the intended use context clear: creating a new group and simultaneously seeding members from various sources. This implicitly distinguishes it from later-stage member operations, but it never explicitly names alternatives or states when NOT to use this tool (e.g., 'to add members to an existing group, use neuron_add_group_members instead'). A small explicit routing note would push this to a 5.

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