Skip to main content
Glama

Create or update concept

upsert_concept
Destructive

Write a concept note into the vault (creates or overwrites the markdown file, then reindexes it). Use to capture new product knowledge discovered during a task — a decision made, a constraint hit, a pattern adopted — so future agents can find it. Omit id to derive a slug from the title; pass an existing id to update that note. Body is markdown; [[wiki-links]] to other concept ids create graph edges. Returns the saved concept's metadata.

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": {
      "title": "<title>",
      "body": "<body>"
    },
    "name": "upsert_concept"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoConcept id (slug). Omit to derive from title; pass an existing id to update.
bodyYesMarkdown body. [[other-id]] wiki-links become graph edges.
tagsNoTags for filtering.
typeNoConcept type (default "concept"). The 14 built-in types are concept, domain, feature, story, spec, workflow, task, decision, constraint, pattern, glossary, iteration (a time-box such as a sprint) and milestone (a scoped deliverable with a target date) and epic (an overarching body of work that tasks and features are part_of); a vault may also define custom types. An unknown type falls back to "concept".
titleYesHuman-readable title (required, non-empty).
doneAtNoFor tasks: ISO timestamp when completed.
statusNoLifecycle status (default "active").
endDateNoFor iterations/milestones: end or target day YYYY-MM-DD (null clears it).
productNoProduct grouping key.
takenAtNoFor tasks: ISO timestamp when claimed.
takenByNoFor tasks: label of the agent/orchestrator that claimed it.
estimateNoFor tasks: story points (null clears it).
codeAreasNoRough codebase paths/globs where this knowledge lives, e.g. ["packages/core/src/vault.ts", "apps/web/src/routes/**"] — lets agents briefed by get_context know where to apply it.
relationsNoTyped edges, e.g. {"depends_on": ["auth-system"]}. Conventions: part_of (feature/story/task → domain), realized_by (story → features), realizes (task → stories/features), governs (spec → what it constrains), governed_by (task → specs), depends_on, constrains, supersedes, related_to. For domain concepts, prefer linking to OTHER domains (related_to / depends_on) wherever they share a boundary or hand off responsibility — connected domains reveal how the product's areas overlap instead of floating as isolated islands.
startDateNoFor iterations/milestones: start day YYYY-MM-DD (null clears it).
taskStatusNoFor type="task" concepts: lifecycle "open" | "taken" | "done" (default "open"). Prefer the task tools (create_task / take_task / complete_task) over setting this directly.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / type / description
      Previous value: -"Concept type (default \"concept\"). The 13 built-in types are concept, domain, feature, story, spec, workflow, task, decision, constraint, pattern, glossary, iteration (a time-box such as a sprint) and milestone (a scoped deliverable with a target date); a vault may also define custom types. An unknown type falls back to \"concept\"."New value: +"Concept type (default \"concept\"). The 14 built-in types are concept, domain, feature, story, spec, workflow, task, decision, constraint, pattern, glossary, iteration (a time-box such as a sprint) and milestone (a scoped deliverable with a target date) and epic (an overarching body of work that tasks and features are part_of); a vault may also define custom types. An unknown type falls back to \"concept\"."
  2. Changed4 schema fields changed
    • addedInput schema / properties / endDate
      Added value: +{
      +  "anyOf": [
      +    {
      +      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "For iterations/milestones: end or target day YYYY-MM-DD (null clears it)."
      +}
    • addedInput schema / properties / estimate
      Added value: +{
      +  "anyOf": [
      +    {
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "For tasks: story points (null clears it)."
      +}
    • addedInput schema / properties / startDate
      Added value: +{
      +  "anyOf": [
      +    {
      +      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "For iterations/milestones: start day YYYY-MM-DD (null clears it)."
      +}
    • changedInput schema / properties / type / description
      Previous value: -"Concept type (default \"concept\"). The 11 built-in types are concept, domain, feature, story, spec, workflow, task, decision, constraint, pattern, glossary; a vault may also define custom types. An unknown type falls back to \"concept\"."New value: +"Concept type (default \"concept\"). The 13 built-in types are concept, domain, feature, story, spec, workflow, task, decision, constraint, pattern, glossary, iteration (a time-box such as a sprint) and milestone (a scoped deliverable with a target date); a vault may also define custom types. An unknown type falls back to \"concept\"."
  3. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare this as non-read-only and destructive, and the description adds concrete meaning: it creates or overwrites the markdown file and then reindexes it. It also says it returns the saved concept's metadata, though permissions and failure behavior are not covered.

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

Conciseness5/5

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

The description is compact and front-loaded: it starts with the write action, then explains usage, id behavior, markdown/wiki-link semantics, and the return value. Every sentence carries useful information without filler.

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 16-parameter mutation with nested relations and no output schema, the description covers the write model, create-vs-update selector, reindex side effect, body graph semantics, and return value. The remaining parameter details are well covered by the schema, though explicit sibling routing is missing.

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%, so the schema already documents all 16 parameters in detail. The description reinforces id derivation and body wiki-link edge creation, but adds little parameter meaning beyond what the schema provides.

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

Purpose4/5

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

States a specific write action and resource ('concept note into the vault') and explicitly distinguishes create-vs-update behavior via the id parameter. It does not explicitly contrast itself with sibling tools such as create_task or link_concepts, so it falls short of a 5.

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 a clear trigger for use: capturing new product knowledge discovered during a task, such as decisions, constraints, or patterns, so future agents can find it. It also explains id omission vs existing id for update, but does not name when-not-to-use cases or alternative sibling tools.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources