Skip to main content
Glama
l33tdawg

(S)AGE

by l33tdawg
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Hybrid

sage_task

Create and update persistent backlog tasks that survive across sessions. Track planned work, feature ideas, and bugs; mark status or link related memories without losing context.

Instructions

Create or update a task in your persistent backlog. Tasks are memories that don't decay while open — they persist until explicitly completed or dropped. Use this to track planned work, feature ideas, bug reports, and anything that should survive across sessions. To create: provide content; an omitted domain uses your approved app-v23 owned home domain, while an explicit domain is never remapped. To update status: provide memory_id + status. To link related memories without changing status: provide memory_id + link_to (array of memory IDs). Task content is immutable after creation. Creation is permanently idempotent: when idempotency_key is omitted, SAGE derives one from the caller, resolved domain, and canonical task content. Repeating the same semantic task returns the original task at its current status, including done or dropped; it never silently creates another task. To intentionally create another task with identical content and domain, supply a new explicit idempotency_key.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
domainNoDomain tag for the task. Omit to use your approved app-v23 owned home domain (legacy nodes use general). Explicit values are never silently remapped.
statusNoTask status. New tasks default to planned; existing tasks require an explicit mutable status.
contentNoTask description (for creating new tasks)
link_toNoMemory IDs to link this task to (max: 20)
memory_idNoExisting task memory ID (for updates). A unique prefix of at least 8 characters is accepted and resolved against this agent's open tasks, so a predecessor named only by prefix in an older entry can be closed directly; an ambiguous prefix returns an error naming the matches.
idempotency_keyNoOptional permanent creation identity. Omit to derive one deterministically from the caller, resolved domain, and canonical task content; every later identical call returns that existing task even after it is done or dropped. Supply a new explicit key only when intentionally creating another task with the same content and domain.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv11.20.2
    • changedInput schema / properties / memory_id / description
      Previous value: -"Existing task memory ID (for updates)"New value: +"Existing task memory ID (for updates). A unique prefix of at least 8 characters is accepted and resolved against this agent's open tasks, so a predecessor named only by prefix in an older entry can be closed directly; an ambiguous prefix returns an error naming the matches."
  2. Changed2 schema fields changedv11.17.4
    • changedInput schema / properties / link_to / description
      Previous value: -"Memory IDs to link this task to"New value: +"Memory IDs to link this task to (max: 20)"
    • addedInput schema / properties / link_to / maxItems
      Added value: +20
  3. Changed3 schema fields changedv11.16.2
    • removedInput schema / properties / domain / default
      Removed value: -"general"
    • changedInput schema / properties / domain / description
      Previous value: -"Domain tag for the task"New value: +"Domain tag for the task. Omit to use your approved app-v23 owned home domain (legacy nodes use general). Explicit values are never silently remapped."
    • addedInput schema / properties / idempotency_key
      Added value: +{
+  "description": "Optional permanent creation identity. Omit to derive one deterministically from the caller, resolved domain, and canonical task content; every later identical call returns that existing task even after it is done or dropped. Supply a new explicit key only when intentionally creating another task with the same content and domain.",
+  "type": "string"
+}
  4. Addedv11.14.2
  5. Removedv11.13.8
  6. Addedv8.1.0
  7. Removedv8.0.0
  8. Addedv7.6.1
  9. Removedv7.5.9
  10. First observedv4.5.2

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly: tasks don't decay, content is immutable, creation is permanently idempotent, idempotency_key derivation is deterministic, explicit domains are never remapped, and repeated semantic tasks return the original task. This is far beyond a minimal mutation warning.

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?

The description is front-loaded with the core purpose and organized into use-case, mode, and invariant sections. It is dense but occasionally restates idempotency behavior in multiple sentences, so it is slightly longer than strictly necessary.

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?

The description covers the main behaviors, statuses, domain resolution, linking, and idempotency rules, which is substantial for a 6-parameter tool. However, with no output schema, it does not describe the return payload or broader pipeline effects, leaving a minor completeness gap.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful cross-parameter semantics: content for creation, memory_id + status for status updates, memory_id + link_to for linking, default home-domain behavior, and idempotency_key nuances. These usage constraints are not fully inferable from the individual parameter descriptions.

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: 'Create or update a task in your persistent backlog.' It also gives concrete use cases ('track planned work, feature ideas, bug reports') and distinguishes the tool from generic memory tools by emphasizing tasks as persistent backlog items.

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?

Provides explicit invocation modes: 'To create: provide content', 'To update status: provide memory_id + status', 'To link related memories...'. It also says when to use the tool ('track planned work...'). It does not explicitly name alternate sibling tools or state when not to use them, so it lacks full exclusion guidance.

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

Deploy Server

Other Tools