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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the bar is lower. The description does add genuine context beyond that — 'leads is the whole list' warns of replacement semantics, and 'two-step' warns that add/delete are not single-call — but it never explains the confirm_token parameter that presumably carries the second step, leaving the destructive flow underspecified.

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 the verb and kept to a single sentence, so it is efficient. But the telegraphic field list ('name, add, remove, leads ..., or delete: true') reads as an unordered run-on and sacrifices clarity for brevity.

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?

This is a destructive, non-idempotent, 8-parameter mutation with a confirmation handshake and a near-duplicate sibling, and the definition leaves the two-step mechanics, the required site argument, and the sibling choice all unaddressed. The output schema is present, so return values need not be covered, but the input-side gaps are substantial.

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 only 13%, so the description must carry the parameter burden. It clarifies leads and delete and lists add/remove/name, but omits the required 'site' parameter entirely, gives no format for 'group', never clarifies that add/remove take emails (only leads is annotated as 'emails'), and leaves the critical confirm_token completely unexplained.

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 a specific verb and resource ('Saves a user group') and enumerates the mutable fields, so an agent can tell it is a membership/group write operation. It never differentiates itself from the sibling tool 'save_group', leaving the agent to guess which of the two near-identically named tools to call.

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?

There is no statement of when to use this versus 'save_group', 'save_list', or 'remove_user', and no prerequisites or exclusions. The only guidance-like sentence ('Adding and deleting are two-step') hints at a workflow but does not say how to complete it or when to prefer add/remove over re-sending the whole group.

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