Skip to main content
Glama
Sign In

Summer

by ai.gosummer
OverviewDiscussionsAdmin

Draft one action family's change to the saved company execution policy and preview it

summer_autonomy_policy_family_preview
Read-onlyIdempotent

Draft one action family's change to the saved company execution policy and preview it. widen adds an automatic rule for a family that reports.autonomy_calibration marks ready_to_widen: at least 30 decided plans and under 1% errors in 14 days. hold adds the family's kill switch: a review rule with threshold 100 that holds every action in the family whatever the other rules say. Returns the drafted settings, the expected version and the autonomy.policy.preview result with its preview_hash. Saves nothing; a person publishes the change with autonomy.policy.update. Money stays within the policy's money limits, and Slack posts still wait unless a rule names Slack.

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>",
      "family": "<family>"
    },
    "name": "summer_autonomy_policy_family_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
changeNowiden adds an automatic rule for a family the calibration report marks ready_to_widen. hold adds the family's kill switch: a review rule with threshold 100. Either way nothing is saved.widen
familyYesThe action family to change.
companyYesSummer company ID
thresholdNoFor widen: the confidence each action in the family needs. Default: the policy's default threshold.
environmentYesEnvironment that owns the resource

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds real context beyond that: nothing is persisted, the change waits for human publication, money stays inside policy limits, and Slack posts still need a named rule. It also describes the return payload (drafted settings, expected version, preview result and hash).

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?

Front-loaded with purpose in the first sentence, then mode semantics, then return values and guardrails. Sentences are dense but each carries a distinct fact; a short list format for widen/hold/returns could make skimming easier, but nothing is filler.

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

Completeness5/5

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

No output schema exists, and the description compensates by naming the returned values including preview_hash. It also covers the human-in-the-loop follow-up, the kill-switch effect, and the money/Slack safety constraints, leaving no material gap for an agent deciding whether and how to call it.

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. The description adds meaning beyond the schema by quantifying the widen criterion (at least 30 decided plans and under 1% errors in 14 days) and spelling out what the hold threshold of 100 does in practice.

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?

States a specific verb and resource: draft one action family's change to the saved execution policy and preview it. It names the scope (one family, not the whole policy), distinguishing it from summer_autonomy_policy_preview and summer_autonomy_policy_update, which is mentioned as the publishing step.

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?

Explains the two modes and when each applies: widen for families that reports.autonomy_calibration marks ready_to_widen, hold to insert a kill switch. It also states that nothing is saved and that a person must publish via autonomy.policy.update, which tells the agent this is not the committing step. It doesn't explicitly contrast with summer_autonomy_policy_preview.

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