(Admin only) Delegate a capability to a user — e.g. 'create_team_space' or 'manage_team_space' so a Curator/Lab Member can create/manage team spaces. Grantable: create_private_space, create_team_space, manage_team_space, ingest, recover, read_private (NOT the admin-only 'grant'/'sparql_admin').
| Name | Required | Description | Default |
|---|---|---|---|
| member | Yes | ||
| capability | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries full behavioral burden. It adds critical auth context ('Admin only'), enumerates valid capabilities, and explicitly excludes forbidden ones. This goes beyond the schema. It lacks details on side effects (e.g., idempotency, whether existing grants are replaced) but the auth and capability constraints are valuable.
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?
Two sentences, front-loaded with 'Admin only' and the core action. The examples and the grantable list are concise and necessary for correct invocation. No filler.
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 two-parameter tool with no output schema and no annotations, the description is reasonably complete. It provides purpose, auth requirement, valid values, and exclusions. It omits error handling or return behavior, but these are not essential for such a simple grant operation. The absence of member format detail is a minor gap.
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%, so the description must compensate. It richly clarifies the 'capability' parameter by listing valid values and examples. However, the 'member' parameter is only described indirectly as 'to a user', without specifying expected format (username, email, user ID). This partial compensation gives a middling score.
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 the action: 'Delegate a capability to a user' and provides concrete examples ('create_team_space', 'manage_team_space') and a full list of grantable capabilities. It distinguishes from sibling tools like brainkb_grant_role_capability by emphasizing the target is a user, and the admin-only restriction further clarifies scope.
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 marks the tool as admin-only and lists allowable capabilities, including an explicit exclusion of admin-only capabilities ('NOT the admin-only grant/sparql_admin'). It does not explicitly name alternative tools for role-level grants, but the user focus and capability list make the intended use clear. Missing explicit 'when not to use' via alternative tool names, but partial exclusion is present.
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.