Emero

Save to emero brain

save_to_emero_brain

Save ONE real decision the user made (a rule, a look, a subject to reuse, a decision, or "remember this") into this brand's emero brain; later generations in any chat reuse it. kind: rule (must/never/prefer) · preference (a leaning) · subject (asset_kind + image_job_ids) · decision · look (detail = the full look-lock sheet). scope "project" or "brand", required for rule/preference/decision. Reported conflicts stay active: supersede only if the user's message replaces them, else ask. Save ONLY what the user said or did; never invent rules. load_skill("emero-brain") for when to use each kind and scope.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "kind": "<kind>",
      "title": "<title>",
      "summary": "<summary>"
    },
    "name": "save_to_emero_brain"
  }
}

Input Schema

Name	Required	Description
`kind`	Yes
`scope`	No
`title`	Yes
`detail`	No
`summary`	Yes
`asset_kind`	No
`project_id`	No	Opaque per-chat project id: "p-" plus 6 random letters and digits. Every chat is a new project. Mint one on your first emero call and pass that SAME id on every call in this chat. Never mint a second one in the same chat, even for a new topic, campaign or subject. Only when the user asks to continue an earlier project, reuse its id from get_emero_brain's project list.
`project_name`	No	Short human title for the project (2-5 words from the user request, e.g. "Perfume ad campaign"). Pass it on your first generate/ingest_url so the project is not left "Untitled". You may also rename at will later — pass an updated project_name (on a generate/ingest_url, or on set_settings with no other change) whenever the user asks, e.g. "call this project cats".
`image_job_ids`	No	subject: its reference image ids, first = primary (job:<uuid>#0, upload:<id>, memory:<id>).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

addedInput schema / properties / image_job_ids / description

Added value: +"subject: its reference image ids, first = primary (job:<uuid>#0, upload:<id>, memory:<id>)."

Changed1 schema field changedOct 26, 2026

changedInput schema / properties / project_id / description

Previous value: -"Opaque per-chat project id. Mint one on your first emero action, pass that SAME id every call. One project per chat: NEVER mint a second for a new topic/campaign/subject/vibe — all stay in the one project; a new id is only for a new chat (server folds a stray id back in). A new chat the user says continues an earlier project reuses that project's id (from get_emero_brain's project list)."New value: +"Opaque per-chat project id: \"p-\" plus 6 random letters and digits. Every chat is a new project. Mint one on your first emero call and pass that SAME id on every call in this chat. Never mint a second one in the same chat, even for a new topic, campaign or subject. Only when the user asks to continue an earlier project, reuse its id from get_emero_brain's project list."

First observedOct 26, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare non-read-only, non-destructive, non-idempotent, so the description is free to add semantics: memories persist and are reused by later generations, and conflicting entries stay active rather than being silently overwritten. That conflict/supersede behavior is exactly the non-obvious trait an agent needs and is not derivable from the annotations. It stops short of saying what happens on a duplicate title or what the call returns.

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 persistence payoff, then packed with dense semicolon-separated constraints. Every clause carries operational content, though the middle-kind enumeration reads as a run-on and could be broken into a short list for faster scanning.

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 9-parameter mutation tool with no output schema, the definition covers the decision-critical ground: what to save, the kind taxonomy, conditional scope, and conflict handling, with an escape hatch to load_skill for the full matrix. Remaining gaps are minor — no statement of the call's response or of duplicate-handling on an identical title.

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

Parameters4/5

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

Schema coverage is only 33% across 9 parameters, and the description compensates well for the weakest ones: it defines each 'kind' enum value (rule = must/never/prefer, preference = a leaning, subject = asset_kind + image_job_ids, look = detail is the full look-lock sheet) and states that scope is required for rule/preference/decision. title, summary, and the conditional asset_kind requirement are left to inference.

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 ('Save ONE real decision ... into this brand's emero brain') plus the downstream effect ('later generations in any chat reuse it'). It enumerates the five kinds inline, which lets an agent distinguish this write path from the read path (get_emero_brain) and the maintenance path (manage_emero_brain) without opening a 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 explicit when-to-save ('only what the user said or did; never invent rules') and a conflict-resolution rule ('supersede only if the user's message replaces them, else ask'), and routes deeper kind/scope selection to load_skill("emero-brain"). It does not name the sibling used for editing or deleting existing memories (manage_emero_brain), so the alternative-tool routing is implied rather than stated.

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

All Emero tools Inspect

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.