Skip to main content
Glama
Sign In

aidelly

by io.github.wilzer
OverviewDiscussionsAdmin

Add Brain Entry

aidelly_add_brain_entry

Add knowledge to the selected workspace Brain when the user asks to remember or save it. Requires workspace settings permission. Save confirmed brand facts, voice, audience, offers, proof, stories, beliefs, pillars or lessons. Intended for confirmed knowledge rather than invented facts or transient drafts. Search first to avoid duplicates. The entry appears in Brain and legacy Memory; embeddings may finish later. If queued is true, the memory is already saved: do not repeat with a new idempotency_key. If pin_applied is false, saving still succeeded but pinning did not. Set scope=agency only when the user explicitly asks to save agency-wide knowledge for all client workspaces: it needs the agency owner or staff with Agency Brain permission, cannot be pinned, and returns memory_id null (use entry.id). Reuse idempotency_key on retries.

Input Schema

NameRequiredDescriptionDefault
bodyNoOptional body override for endpoints with sparse parameter schemas.
tagsNo
typeYes
queryNoOptional query overrides for endpoints with sparse parameter schemas.
scopeNoTarget Brain. workspace (default) saves memory-backed knowledge to the selected workspace. agency saves to the agency Brain shared with the agency's client workspaces; it needs the agency owner, or Agency Team staff with manage_agency_brain, on the Agency plan. Agency entries have no memory_id; use entry.id.workspace
titleYes
pinnedNoPin the entry. Not supported for scope=agency (400 BRAIN_AGENCY_PIN_UNSUPPORTED); pin agency entries in the Brain page.
contentYes
brand_idNo
platformsNo
importanceNo
valid_untilNo
workspace_idNoWorkspace to operate in: the `id` of a workspace returned by aidelly_list_workspaces. Optional for read operations; required when creating content.
idempotency_keyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / pinned / description
      Added value: +"Pin the entry. Not supported for scope=agency (400 BRAIN_AGENCY_PIN_UNSUPPORTED); pin agency entries in the Brain page."
    • addedInput schema / properties / scope
      Added value: +{
+  "default": "workspace",
+  "description": "Target Brain. workspace (default) saves memory-backed knowledge to the selected workspace. agency saves to the agency Brain shared with the agency's client workspaces; it needs the agency owner, or Agency Team staff with manage_agency_brain, on the Agency plan. Agency entries have no memory_id; use entry.id.",
+  "enum": [
+    "workspace",
+    "agency"
+  ],
+  "type": "string"
+}
  2. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only say not-read-only, open-world, non-destructive; the description supplies the operational context they omit: workspace-settings permission requirement, agency-owner/manage_agency_brain requirement for scope=agency, queued/pin_applied/memory_id return semantics, delayed embeddings, and idempotency_key reuse on retries. This is far beyond what structured fields provide.

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 purpose and trigger, then permission and edge-case behavior in descending priority. Most sentences earn their place, though the enumerated knowledge types largely restate the `type` enum and could be trimmed.

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

Completeness4/5

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

For a 14-parameter mutation tool with no output schema, the description compensates well by explaining the response flags (queued, pin_applied, memory_id null for agency) and permission prerequisites. Remaining incompleteness is limited to the undocumented secondary parameters.

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 coverage is only 36% across 14 parameters, so the description must carry weight. It clarifies the trickiest ones (idempotency_key retry reuse, scope=agency semantics, pinned being unsupported for agency), but many parameters (importance, valid_until, tags, platforms, brand_id, content limits) remain undocumented in both the schema and the description.

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 and resource ('Add knowledge to the selected workspace Brain') plus the trigger ('when the user asks to remember or save it'). The enumerated knowledge types and the distinction from 'confirmed knowledge rather than invented facts or transient drafts' separate it cleanly from siblings like aidelly_add_brain_document and aidelly_update_brain_entry.

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

Usage Guidelines5/5

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

Gives explicit when (user asks to remember/save confirmed brand facts), when-not (invented facts, transient drafts), a de-duplication alternative ('Search first to avoid duplicates'), and a narrow conditional path for scope=agency with its own permission preconditions. Routing guidance is complete enough to act on without opening other schemas.

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

All aidelly 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