Skip to main content
Glama

dialogbrain

by io.github.saloprj
OverviewDiscussionsAdmin

integrations_sync_knowledge

Refresh a knowledge collection from an integration's endpoints, for content too large to return in a tool response (a 300KB+ catalogue an agent could never fit in one call). Pass sources + collection to configure and run in one step — they are stored on the integration, so later runs need only integration_id. Every run is a FULL refresh; a source whose rendered text is unchanged is skipped (reported unchanged) rather than re-uploaded. Returns a per-source report: created / updated / unchanged / no_records / error.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
forceNoRe-upload and re-index every source even when its rendered text is unchanged. Use after a fix BELOW the text — chunking, extraction, embeddings — which the content digest cannot see (without this the only repair was deleting the synced files by hand).
sourcesNoSources to store on the integration and then sync. OMIT to re-run whatever is already stored. REPLACES the stored list wholesale — pass every source you want, not just a new one, or the omitted ones stop syncing. Each item: {operation_id (from integrations.get_endpoints), arguments? (e.g. {"locale": "ru"}), title?, spec, endpoint?}. `endpoint` {method, path} lets the sync call an operation NOT registered on the integration (kept off the agent tool surface — e.g. a 300KB catalogue). `spec` is the projection: {records (REQUIRED dotted path to the row list), envelopes?, recurse?, title?, body?, meta?, drop?, max_chars?}. Same operation with different `arguments` is a separate document, which is how one endpoint serves four locales.
collectionNoKnowledge collection to publish into, created if absent. Required when `sources` is given; ignored otherwise.
descriptionNoDescription for a newly created collection. Optional.
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
integration_idYesIntegration id (from integrations.list) to sync.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / in_workspace
      Added value: +{
+  "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
+  "type": "integer"
+}
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare the safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=false); the description adds real behavior the agent cannot infer: every run is a FULL refresh, unchanged sources are skipped and reported as `unchanged`, `sources` REPLACES the stored list wholesale, and `force` exists because the content digest cannot see chunking/extraction/embedding changes. It also enumerates the per-source return categories.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and the reason it exists, then layered with the one-step-vs-later-run distinction and the return report. Dense but not padded; some sentences carry stacked parentheticals that slightly slow parsing, which keeps it from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description supplies the return shape (created/updated/unchanged/no_records/error), covers the full-refresh and skip semantics, the wholesale-replacement hazard, and the `force` escape hatch. For a 6-parameter mutation tool this is complete enough to call correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the schema descriptions for `force`, `sources`, `collection`, and `integration_id` are already highly detailed, so baseline is 3. The description adds the persistence model (sources/collection are stored on the integration, so later runs need only `integration_id`) and the fact that the same operation with different `arguments` is a separate document, but most parameter-level detail lives in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (refresh a knowledge collection from an integration's endpoints) and immediately gives the distinguishing use case: content too large to return in a tool response. An agent can tell this apart from integrations_execute_tool or collections_refresh_website without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear conditional guidance: pass `sources`+`collection` to configure and run in one step, later runs need only `integration_id`, and `force` is for repairs below the text layer. It stops short of naming sibling alternatives explicitly (e.g. when to use integrations_execute_tool or collections_add_website instead), so it is clear context rather than full routing guidance.

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

All dialogbrain toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources