List where a knowledge base you own is attached (agent / department / personal), each with its attachment id and mode (tool | auto_inject | both). Use an attachment id with findagent_detach_kb to remove that one binding. READ-ONLY.
| Name | Required | Description | Default |
|---|---|---|---|
| kb_id | Yes | The knowledge base id (from findagent_list_kbs). |
| Name | Required | Description | Default |
|---|---|---|---|
| usage | No | ||
| attachments | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description confirms the read-only behavior already present in annotations and adds meaningful context: the KB must be owned, the result includes attachment ids and modes, and the identifier is intended for detaching a binding. This goes beyond the annotation flags without contradicting them.
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 carry the entire message: the first states the operation and output shape, the second links the output to the relevant sibling. There is no filler or repetition of schema fields.
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?
With a single parameter, a clear output schema, and read-only annotations, this description covers everything an agent needs to select and call the tool correctly. It also provides the cross-reference to detach, which completes the workflow context.
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?
The only parameter, kb_id, is fully documented in the schema with 100% coverage and its source (findagent_list_kbs). The description adds the ownership requirement ('a knowledge base you own') and clarifies what the returned attachment ids are for, giving the parameter practical context beyond the raw type.
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 specific verb ('List') and a precise resource ('where a knowledge base you own is attached'), then names the three attachment targets (agent / department / personal) and what each row contains (attachment id, mode). This differentiates it from sibling tools like findagent_attach_kb and findagent_detach_kb without needing their schemas.
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?
It states the tool's scope ('knowledge base you own') and explicitly ties the returned attachment id to findagent_detach_kb, giving a concrete follow-up use. It does not spell out exclusion criteria versus all siblings, but the purpose is clear enough that an agent can infer when it applies.
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.
Every tool targets a clearly scoped resource+action combination, and the versioning variants (bump_version vs repull vs reintrospect_mcp) are explicitly disambiguated by agent kind. Even with 52 tools, the descriptions make each purpose distinct enough to avoid misselection.
Nearly all tools follow the findagent_<verb>_<object> snake_case pattern, and families share predictable verbs like list, create, delete, edit, and submit. Minor exceptions such as findagent_preflight, findagent_whoami, and findagent_earnings keep it from perfect consistency.
At 52 tools, this far exceeds the 25-tool threshold for a coherent MCP surface. The count may reflect a broad platform, but as a single toolset it is heavy and likely to strain agent selection and context.
The surface covers publishing, versioning, knowledge bases, org management, GitHub import, purchases, and the demand board in impressive depth. However, there are notable dead ends: no unpublish/delete for a live agent, no request-fulfillment/linking action, and no org deletion or KB document update.
