Skip to main content
Glama

ouroboros_evolve_step

Run one generation of an evolutionary code-generation loop. Reconstructs lineage state from events, evaluates, and returns a convergence signal with the next action.

Instructions

Run exactly ONE generation of the evolutionary loop. For Gen 1: provide lineage_id and seed_content (YAML). For Gen 2+: provide lineage_id only (state reconstructed from events). Returns generation result, convergence signal, and next action (continue/converged/ontology_stable/stagnated/exhausted/failed). ontology_stable is a non-success handoff; rerun the same lineage with execute=true to perform Execute→Evaluate.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
executeNoWhether to run seed execution and evaluation. True (default): full pipeline with Execute→Validate→Evaluate. False: ontology-only evolution (fast, no execution).
skip_qaNoSkip post-execution QA evaluation. Default: false
parallelNoWhether to run ACs in parallel. True (default): parallel execution (fast, may cause import conflicts). False: sequential execution (slower, more stable code generation).
lineage_idYesLineage ID to continue or new ID for Gen 1
project_dirNoProject root directory for validation (pytest collection check). If omitted, auto-detected from execution output or CWD.
execution_idNoOptional execution id for checkpoint commit metadata.
seed_contentNoSeed YAML text for Gen 1. Pass a YAML-formatted string (for example, newline-delimited 'goal: ...' fields), not JSON-shaped text or an object literal; some MCP clients may otherwise coerce the value to an object before Ouroboros receives it. Omit for Gen 2+ (seed reconstructed from events).
commit_policyNoOptional checkpoint commit policy for passed ACs.
auto_session_idNoOptional auto session id for checkpoint commit metadata.
benchmark_controlNoRun a deliberate full-graph frugality control. Default: false. Requires execute=true, Gen 2+, an explicit Git project_dir, and a clean baseline; unavailable through plugin delegation.
checkpoint_commitsNoExisting checkpoint commit records for idempotency.
conductor_directiveNoBounded corrective context for this successor generation.
conductor_decision_idNoSelected conductor decision authorizing this successor generation.
recover_expired_claimNoExplicitly recover an expired lineage writer claim after confirming the prior owner process is dead. Default: false
predecessor_execution_idNoExecution or generation that this successor follows.
checkpoint_attempted_ac_idsNoAcceptance criteria already considered for checkpoint commits.
Behavior4/5

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

With no annotations, the description carries the transparency burden and does add useful behavior: it is a single-step operation, state is reconstructed from events in later generations, and ontology_stable is a non-success handoff requiring a rerun with execute=true. It does not explicitly state side effects such as event/checkpoint writes or system modifications, which would make it fully transparent.

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 with the primary purpose; every clause adds operational information (generation rule, return values, next-action enum, ontology_stable handoff). No filler or repetition of schema-only content.

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 complex 16-parameter tool with no output schema and no annotations, the description covers the core loop semantics, input requirements, return summary, and next-action vocabulary. It does not provide detailed return shape or failure handling, but the rich schema plus this workflow narrative is reasonably complete.

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 description coverage is 100%, so the baseline is 3. The description adds generation-specific semantics beyond the schema by telling the caller which parameters are relevant for Gen 1 vs Gen 2+ and by explaining that execute=true is used to move past ontology_stable. This enriches the meaning of lineage_id, seed_content, and execute.

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 opens with a specific action: 'Run exactly ONE generation of the evolutionary loop,' which names both the verb and resource. It also segments Gen 1 vs Gen 2+ usage, making the tool's distinct role among evolve/auto siblings clear.

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 explicit input requirements per generation ('Gen 1: provide lineage_id and seed_content', 'Gen 2+: provide lineage_id only') and how to handle the ontology_stable handoff with execute=true. It does not explicitly contrast with sibling tools like ouroboros_auto or ouroboros_start_evolve_step, so it stops short of full alternatives guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Q00/ouroboros'

If you have feedback or need assistance with the MCP directory API, please join our Discord server