Spaces by Peakflo

graph_record_decision

Record a decision in the lineage store and expose it as a Business Context -> Graph entity. Supply a Graph entity ID or a subject type and ID. Use after making a decision.

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": {
      "decision_type": "<decision_type>",
      "outcome": "<outcome>",
      "reasoning": "<reasoning>"
    },
    "name": "graph_record_decision"
  }
}

Input Schema

Name	Required	Description
`outcome`	Yes	The decision outcome (e.g., approved, rejected, escalated)
`exception`	No	If this is an exception to normal policy, explain why
`reasoning`	Yes	Explanation of why this decision was made
`decided_at`	No	Original decision time (ISO 8601); supply source_decision_id with it
`entity_ids`	No	IDs of entities this decision concerns
`subject_id`	No	ID of the primary subject when no Graph entity ID is supplied
`record_refs`	No	References to records in golden tables
`subject_name`	No	Human-readable name of the primary subject
`subject_type`	No	Type of the primary subject when no Graph entity ID is supplied
`decision_type`	Yes	Type of decision (e.g., approval, rejection, exception, override, matching)
`policy_applied`	No	Which policy or rule was applied
`outcome_category`	No	Generic outcome category for domain-specific outcomes
`source_decision_id`	No	Stable source ID for retries; supply decided_at with it

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already establish that this is a non-read-only, non-destructive, closed-world write. The description adds real context: the decision is persisted in a lineage store and materialized as a Graph entity, which implies a visible side effect beyond storage. It does not cover idempotency/duplicate handling (despite source_decision_id existing for retries) or what is returned on success.

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?

Three short sentences, front-loaded with the action and destination before the prerequisite. No filler, though the second and third sentences could be merged into a single usage line without loss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter mutation with no output schema, the definition covers purpose, destination, and targeting but omits the write's observable result, duplicate/conflict behavior, and how retries interact with source_decision_id. It is adequate to attempt a call but leaves meaningful operational questions unanswered.

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 coverage is 100%, so the baseline is 3, and the description earns an extra point by stating the either/or targeting rule (Graph entity ID vs. subject type and ID) that ties entity_ids, subject_type, and subject_id together into one choice. It still says nothing about the many optional fields such as record_refs, policy_applied, or outcome_category.

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?

The description names a specific verb and resource ("Record a decision") plus its destination ("lineage store") and a secondary effect ("expose it as a Business Context -> Graph entity"). That separates it from read-oriented siblings such as graph_decision_detail and graph_decision_lineage, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use after making a decision" gives a clear trigger point, and the ID-or-subject rule conveys a precondition. There is no guidance on when not to use it, how it relates to graph_decision_detail/graph_precedent, or what to do if a decision was already recorded.

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

All Spaces by Peakflo tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.