get_docs_searchEmbeds the query with Ollama (nomic-embed-text) and returns the closest public doc chunks
from the environment's search index (pgvector).
Source: GET /api/v1/docs/search No Authorization header is required. Prefer connection.workspaceName and connection.appId as stable config instead of generating identity fields dynamically.
| Name | Required | Description | Default |
|---|---|---|---|
| auth | No | ||
| body | No | ||
| query | Yes | ||
| params | No | ||
| connection | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral disclosure burden. It does so well by naming the embedding model, the pgvector index, the read/search nature of the call, and the auth requirement. It stops short of describing rate limits or error behavior, but for a search tool the core behavior is transparent enough.
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 compact and well structured: it front-loads the core behavior, then gives the endpoint, auth requirement, and config guidance. Every sentence earns its place, with no filler or redundant restatement of the tool name.
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 5-parameter nested tool with no annotations and no output schema, the description provides the endpoint, behavior, and auth context, but omits the output shape, limit semantics, and empty/error result behavior. It is sufficient to attempt a call, but not fully complete for an agent that needs to interpret results robustly.
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 0% at the top-level parameter envelope, so the description must compensate. It only adds guidance about connection.workspaceName and connection.appId, and does not explain the meaning of q, limit, host, or the body/params fields. The agent is left to infer parameter semantics from nested schema text rather than from the tool 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 clearly states a specific verb and resource: it embeds the query with Ollama and returns the closest public doc chunks from the pgvector search index. It also names the underlying endpoint, making the tool's job unambiguous and distinct from the auth/session siblings.
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 gives clear context: it is a semantic documentation search, requires no Authorization header, and recommends using connection.workspaceName and connection.appId as stable config. It does not explicitly name excluded alternatives, but no sibling tool is a competing docs-search tool, so the absence of direct alternative routing is not a serious gap.
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 target distinct session/auth operations, and the descriptions clearly separate browser redirects from API endpoints. The main ambiguity is between get_sessions and get_sessions_my (payload vs. list) and the two logout variants, though the docs disambiguate them.
API tools consistently use snake_case `{method}_{resource}_{action}` names, but a few deviate: `auth_session_callback` lacks the method prefix, `get_sessions_get_key`/`delete_sessions_delete_key` are redundant, and the `secureflows_*` helpers use a different prefix. Still readable and predictable.
18 tools is slightly above the sweet spot, but the count is justified by distinct session lifecycle operations, auth redirects, and integration helpers. Only `get_docs_search` feels peripheral to the core session domain.
The surface covers session create, get-or-create, read, key-level update/delete, renew, revoke, logout, identity, and self-service listing/revocation, plus login/logout URL builders and linting. No important dead ends for the stated auth/session purpose.