Skip to main content
Glama

sync_state

Records a work check-in to persist EISV and the raw recommendation, then returns the effective governance action so agents can self-correct before failures occur.

Instructions

Record a check-in: persist EISV, preserve the raw recommendation, and return the effective action. Inferred pauses are observational unless the operator enables actuation. A prediction_id — only when you pass confidence — to grade that check-in later with record_result. The first call auto-binds an identity, except under strict identity, which refuses and points at start_session. simulate_update previews a proposed check-in without advancing state, though it still appends an audit event; check_working_state reads the current verdict without writing. process_agent_update is the canonical twin; this name returns a digest envelope, and a routine check-in omits the raw payload (response_mode='full' adds it under raw_governance). EISV field definitions: describe_tool(tool_name='check_working_state').

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": "sync_state"
  }
}

Input Schema

NameRequiredDescriptionDefault
liteNoBoolean alias for response_mode='compact'. Applies only when response_mode is left at 'auto' (an explicit response_mode always wins).
logprobsNoPer-token top-k output logprobs, e.g. [[lp, lp, ...], ...]. Grounds S at tier-1 instead of the heuristic; absent for Claude.
task_typeNoTask type. Core types: convergent | divergent | mixed; 'introspection' for self-examination.mixed
complexityNoTask complexity, strictly 0-1. Check-in aliases also accept 'trivial'|'low'|'medium'|'high'|'very_high'.
confidenceNoConfidence level for this update (0-1, optional).
parametersNoAgent parameters vector (optional, deprecated).
task_labelNoS22 H5 provenance: human-readable bounded task label
sensor_dataNoCaller-published sensor measurements: `eisv` for a physical E/I/S/V reading, `afferents` for raw dimensions. Telemetry only, never a verdict input.
task_outcomeNoS22 H5 provenance: outcome label for the bounded task
ethical_driftNoEthical drift signals (3 components): [primary_drift, declared coherence_loss, complexity_contribution].
response_modeNoResponse shape. 'auto' (default) or 'compact' for routine check-ins; 'mirror' for actionable signals; 'full' for everything.auto
response_textNoAgent's response text (optional, for analysis)
comparison_keyNoS22 H5 provenance: stable key for comparing the same bounded task across harnesses
memory_contextNoS22 provenance: memory/KG/transcript surfaces visible to the writer
epistemic_classNoStorage label for this row: agent_report (default), substrate_observation (measured), substrate_interpretation (derived), prediction (forward claim).agent_report
continuity_tokenNoSame-process rebind proof only; never a cross-process resume.
client_session_idNoBinding id for calls in this process; not a cross-process proof.
provenance_contextNoSituating metadata: harness_type, model_provider, model, transport, tool_surface, governance_mode, verification_source, locus. Descriptive only.
recent_tool_resultsNoSelf-reported tool outcomes from the agent's most recent actions.
trajectory_signatureNoTrajectory identity signature from anima-mcp.
require_strong_identityNoIf true, reject updates unless identity assurance tier is strong.
include_memory_suggestionsNoOpt in to a KG lookup seeded from this check-in and include a few matching discovery digests.
auto_export_on_significanceNoIf true, write a governance history export whenever this check-in is judged significant: a risk spike, a coherence drop, a void threshold …

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv3.1.0
    • changedInput schema / description
      Previous value: -"Share your work and get supportive feedback. Your main tool for checking in."New value: +"Record a work check-in and get a governance decision."
    • changedInput schema / properties / auto_export_on_significance / description
      Previous value: -"If true, automatically export governance history when thermodynamically significant events occur."New value: +"If true, write a governance history export whenever this check-in is judged significant: a risk spike, a coherence drop, a void threshold …"
    • changedInput schema / properties / client_session_id / description
      Previous value: -"In-session binding id from start_session()/identity(); pass it on same-process calls. Not a cross-process proof."New value: +"Binding id for calls in this process; not a cross-process proof."
    • changedInput schema / properties / complexity / anyOf
      Previous value: -[
      -  {
      -    "anyOf": [
      -      {
      -        "type": "number"
      -      },
      -      {
      -        "type": "string"
      -      }
      -    ],
      -    "ge": 0,
      -    "le": 1
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "maximum": 1,
      +    "minimum": 0,
      +    "type": "number"
      +  },
      +  {
      +    "anyOf": [
      +      {
      +        "pattern": "^(0(\\.\\d+)?|1(\\.0+)?|\\.\\d+)$",
      +        "type": "string"
      +      },
      +      {
      +        "enum": [
      +          "complex",
      +          "critical",
      +          "high",
      +          "low",
      +          "medium",
      +          "minimal",
      +          "moderate",
      +          "simple",
      +          "trivial",
      +          "very_high"
      +        ],
      +        "type": "string"
      +      }
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / confidence / anyOf
      Previous value: -[
      -  {
      -    "anyOf": [
      -      {
      -        "type": "number"
      -      },
      -      {
      -        "type": "string"
      -      }
      -    ],
      -    "ge": 0,
      -    "le": 1
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "maximum": 1,
      +    "minimum": 0,
      +    "type": "number"
      +  },
      +  {
      +    "pattern": "^(0(\\.\\d+)?|1(\\.0+)?|\\.\\d+)$",
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / continuity_token / description
      Previous value: -"Ownership proof from onboard()/identity(), for same-live-process rebinds only. Not a cross-process resume credential."New value: +"Same-process rebind proof only; never a cross-process resume."
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations, it discloses that inferred pauses are observational unless actuation is enabled, that the first call auto-binds identity except under strict identity, and that simulate_update still appends an audit event. It also clarifies the digest-envelope return shape and the effect of response_mode='full'.

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 core purpose is front-loaded in the first sentence, and the remaining clauses carry real routing and behavioral detail. It is dense and somewhat fragmentary in places, but there is little outright 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 23-parameter check-in tool with no output schema, the description covers the essential behavior: persistence, identity binding, preview-vs-write distinctions, response modes, and observational-vs-actuation semantics. It does not explain every field, but the schema already does, and it provides a pointer for EISV definitions.

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 already 100%, so the schema carries most parameter meaning. The description nonetheless adds useful semantics: confidence enables later grading via prediction_id, response_mode='full' exposes raw_governance, and EISV field definitions are delegated to describe_tool.

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 verb and resource: 'Record a check-in: persist EISV, preserve the raw recommendation, and return the effective action.' It also distinguishes this tool from key siblings by naming simulate_update for previews, check_working_state for reads, and process_agent_update as the canonical twin.

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 clearly routes the agent to alternatives such as simulate_update and check_working_state, and explains the first-call identity binding plus the strict-identity exception. It stops short of an explicit rule for when to choose sync_state over its canonical twin process_agent_update, leaving that choice partially inferential.

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