Skip to main content
Glama
Sign In

Summer

by ai.gosummer
OverviewDiscussionsAdmin

Publish the complete previewed company execution policy under the authenticated administrator's authority

summer_autonomy_policy_update

Publish the complete previewed company execution policy under the authenticated administrator's authority. Requires a person's delegated messaging.activate grant, expected version and preview_hash. Replaces legacy inbound-channel plan permission. Does not run old held plans.

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": {
      "company": "<company>",
      "environment": "<environment>",
      "version": "<version>",
      "settings": "<settings>",
      "preview_hash": "<preview_hash>"
    },
    "name": "summer_autonomy_policy_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
companyYesSummer company ID
versionYes
settingsYes
environmentYesEnvironment that owns the resource
preview_hashYes
idempotency_keyNoReuse the same key when retrying the same change

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / settings / properties / money / description
      Previous value: -"Money limits for auto-run. Charges and promotions always wait for a person."New value: +"Money limits for auto-run, in whole cents. Omitted: a refund up to 20000 ($200), a credit up to 10000 ($100) and 50000 ($500) in any 24 hours. Set the limits to 0 to make all money wait for a person. Charges and promotions always wait for a person."
  2. Changed1 schema field changed
    • addedInput schema / properties / settings / properties / exceptions / items / properties / family
      Added value: +{
+  "description": "An action family: reply, closure, record, vendor_contact, clinician_note, address_cancel or money. With mode review, the rule holds every action in the family (a kill switch). An automatic family rule does not lift the Slack hold unless it also names the slack channel.",
+  "enum": [
+    "reply",
+    "closure",
+    "record",
+    "vendor_contact",
+    "clinician_note",
+    "address_cancel",
+    "money"
+  ],
+  "type": "string"
+}
  3. Changed2 schema fields changed
    • addedInput schema / properties / settings / properties / money
      Added value: +{
+  "additionalProperties": false,
+  "description": "Money limits for auto-run. Charges and promotions always wait for a person.",
+  "properties": {
+    "creditCentsMax": {
+      "description": "Largest single account credit that may run automatically. Omitted: credits wait for a person.",
+      "maximum": 1000000,
+      "minimum": 0,
+      "type": "integer"
+    },
+    "dailyCentsMax": {
+      "description": "Most refunds and credits that auto-run may approve in any 24 hours, across the company and environment.",
+      "maximum": 1000000,
+      "minimum": 0,
+      "type": "integer"
+    },
+    "refundCentsMax": {
+      "description": "Largest single refund that may run automatically. Omitted: refunds wait for a person.",
+      "maximum": 1000000,
+      "minimum": 0,
+      "type": "integer"
+    }
+  },
+  "required": [
+    "dailyCentsMax"
+  ],
+  "type": "object"
+}
    • addedInput schema / properties / settings / properties / partial
      Added value: +{
+  "description": "When true, auto-run may run the leading steps of a plan that qualify and leave the remaining steps, and every case closure, waiting for a person. Off when omitted.",
+  "type": "boolean"
+}
  4. Added

TDQS

A3.8/5.0
Behavior4/5

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

Beyond the annotations (which only mark it non-read-only, non-destructive, non-idempotent), the description adds the delegated-grant auth requirement, the version/preview_hash concurrency gate, and the fact that it replaces legacy inbound-channel plan permission and won't execute stale held plans. These are meaningful operational disclosures; it omits any version-conflict or idempotency behavior.

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?

Four short sentences, front-loaded with the publish action before prerequisites and caveats. Little waste, though the title largely duplicates the first sentence.

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 complex nested mutation with no output schema, the description covers prerequisites and legacy-replacement behavior but is silent on version-mismatch handling, what happens to the previous policy, and what a successful publish returns. Adequate but leaves gaps an agent would need to discover empirically.

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?

With 50% schema description coverage across six parameters, the description names two required inputs (version, preview_hash) but adds no detail on company, environment, settings, or idempotency_key. The nested settings schema is richly self-documented, so a baseline 3 is fair.

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 states a specific verb and resource ('Publish the complete previewed company execution policy'), and the word 'previewed' ties it to the autonomy preview siblings without naming one. An agent can distinguish this publish action from summer_autonomy_policy_preview, but it stops short of explicitly routing to that sibling.

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 lists concrete prerequisites (a delegated messaging.activate grant, expected version, preview_hash), which tells the agent when the call is valid. 'Does not run old held plans' clarifies a boundary of the operation, though it never explicitly says to call summer_autonomy_policy_preview first.

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

All Summer toolsInspect
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.

Resources