Skip to main content
Glama

Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72%

oxyo_goal

Manage persistent multi-session task dependency graphs (create, decompose, next, update, tree), returning unblocked next tasks and automatically propagating failure blockers. Use for multi-step project roadmaps across sessions; use oxyo_remember_episode for single-step logs.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "oxyo_goal"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of unblocked tasks returned when action='next'.
scopeNoOptional project/repo scope for isolating goal trees.
titleNoConcise actionable goal title (required when action='create').
actionNoOperation: 'create' goal, 'decompose' into subgoals, 'next' unblocked tasks, 'update' status, or 'tree'.next
statusNoNew lifecycle state applied to `goal_id` when action='update'.
goal_idNoTarget goal ID for 'decompose', 'update', or subtree inspection.
evidenceNoVerification output, commit hash, or test summary recorded on status update.
priorityNoScheduling priority from 0.0 (low) to 1.0 (urgent) used to rank 'next' tasks.
subgoalsNoChild goal specs [{'title': ..., 'acceptance_criteria': ...}] when action='decompose'.
parent_idNoOptional parent goal ID when creating a nested sub-goal.
depends_onNoList of prerequisite goal IDs that must complete before this goal unblocks.
failure_causeNoRoot-cause label logged to the causal graph when updating status to 'failed'.
chain_sequentiallyNoAutomatically wire each decomposed subgoal to depend on the preceding subgoal.
acceptance_criteriaNoConcrete verification condition defining when the goal is complete.
prospective_triggerNoOptional context cue or file/topic pattern that surfaces this goal automatically.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changed
    • addedInput schema / properties / acceptance_criteria / description
      Added value: +"Concrete verification condition defining when the goal is complete."
    • addedInput schema / properties / action / description
      Added value: +"Operation: 'create' goal, 'decompose' into subgoals, 'next' unblocked tasks, 'update' status, or 'tree'."
    • addedInput schema / properties / chain_sequentially / description
      Added value: +"Automatically wire each decomposed subgoal to depend on the preceding subgoal."
    • addedInput schema / properties / depends_on / description
      Added value: +"List of prerequisite goal IDs that must complete before this goal unblocks."
    • addedInput schema / properties / evidence / description
      Added value: +"Verification output, commit hash, or test summary recorded on status update."
    • addedInput schema / properties / failure_cause / description
      Added value: +"Root-cause label logged to the causal graph when updating status to 'failed'."
    • addedInput schema / properties / goal_id / description
      Added value: +"Target goal ID for 'decompose', 'update', or subtree inspection."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of unblocked tasks returned when action='next'."
    • addedInput schema / properties / parent_id / description
      Added value: +"Optional parent goal ID when creating a nested sub-goal."
    • addedInput schema / properties / priority / description
      Added value: +"Scheduling priority from 0.0 (low) to 1.0 (urgent) used to rank 'next' tasks."
    • addedInput schema / properties / prospective_trigger / description
      Added value: +"Optional context cue or file/topic pattern that surfaces this goal automatically."
    • addedInput schema / properties / scope / description
      Added value: +"Optional project/repo scope for isolating goal trees."
    • addedInput schema / properties / status / description
      Added value: +"New lifecycle state applied to `goal_id` when action='update'."
    • addedInput schema / properties / subgoals / description
      Added value: +"Child goal specs [{'title': ..., 'acceptance_criteria': ...}] when action='decompose'."
    • addedInput schema / properties / title / description
      Added value: +"Concise actionable goal title (required when action='create')."
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the bar is lower, yet the description still adds real value: cross-session persistence, that `next` returns unblocked tasks, and that failure blockers are propagated automatically. That propagation is a non-obvious cascading side effect an agent needs to know about; only the reversibility of updates and the shape of `tree` output are left unstated.

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?

Two sentences, front-loaded with the core resource and operation set before the routing sentence. Every clause carries information: operations, return behavior, propagation, scope of use, and the alternative tool.

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 15-parameter, action-dispatch tool with no required params, full schema coverage, and annotations covering safety, the description covers purpose, usage scope, and key side effects. It stops short of explaining what non-`next` actions return (e.g. the `tree` payload), which matters somewhat given there is no output schema.

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 every one of the 15 parameters is already self-documenting; the description correctly does not duplicate them. It only implicitly touches parameters via 'returning unblocked next tasks' (limit/priority) and 'failure blockers' (failure_cause), adding no syntax or format guidance beyond the schema, which is the expected baseline case.

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?

The description names a specific resource ('persistent multi-session task dependency graphs') and enumerates the five operations (`create`, `decompose`, `next`, `update`, `tree`), so an agent knows exactly what the tool covers. It also explicitly distinguishes itself from `oxyo_remember_episode` by scoping that sibling to single-step logs.

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?

It gives a clear selection rule: 'Use for multi-step project roadmaps across sessions' with the explicit alternative for single-step logging. What it does not do is help choose among the five actions or state exclusions for other graph-like tasks, so guidance is strong but not exhaustive.

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.