(Admin) Ban a user by email (reversible; preserves history). This is how accounts are removed — there is NO hard delete. Banning an Admin is SuperAdmin-only; SuperAdmin accounts cannot be banned.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | |||
| reason | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses reversibility, history preservation, absence of hard delete, and role-based limitations. Missing details like session/token effects are minor for a ban action.
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 description is two sentences with zero filler, front-loading the primary action and then providing critical context about account removal and permissions.
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 a 2-parameter admin action, the description covers the essential behavioral and access-control aspects. It lacks output details but no output schema exists, and the missing reason parameter explanation is the main gap preventing a 5.
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 0% and the description only explains the email parameter implicitly via 'by email'. The reason parameter is completely unexplained, leaving its format or purpose ambiguous. The description fails to compensate for the sparse schema.
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 clearly states 'Ban a user by email' with specific verb and resource, and adds context that this is the account removal mechanism with no hard delete. This distinguishes it from sibling tools like deactivate_user or unban_user.
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 explicitly says 'This is how accounts are removed' and notes role restrictions (SuperAdmin-only for banning admins, SuperAdmin cannot be banned). This gives clear usage context, though it doesn't explicitly compare to alternatives like unban_user.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes, such as user management (activate, ban, assign role) vs. space management (create, add member, set visibility) vs. ingest/jobs (ingest_files, job_status, recover). A few pairs like grant_capability vs. grant_role_capability are similar but descriptions clarify the target, so an agent should be able to choose correctly.
All tools are prefixed with brainkb_ and the large majority follow a verb_noun pattern (e.g., add_space_member, list_tokens, revoke_token). Some exceptions like brainkb_delta, brainkb_search, brainkb_whoami, and brainkb_capabilities break the pattern, but these are few and still readable.
With 49 tools, the server is far above the 25+ threshold for 'too many'. While the broad scope (user admin, spaces, graphs, ingest, provenance, auth) justifies many operations, the sheer number makes it heavy and potentially unwieldy for an agent to navigate.
The tool set covers a wide range of use cases: user/role/capability management, space administration, graph registration, ingest, job monitoring, provenance, search, and SPARQL. However, there are notable gaps such as removing a space member, deleting a space, or updating space metadata, which could leave agents without a way to fully manage the lifecycle of a space.