Skip to main content
Glama

Soclo

by app.soclo
OverviewDiscussionsAdmin

Save automatic-reply settings

soclo_inbox_settings_save
DestructiveIdempotent

Preview, then with confirm: true save, an exact patch of the automatic-reply settings, including auto_faq and private_buying. Omit choices that should stay unchanged; changing a child choice does not turn AI Inbox on. Needs manage:inbox. Read soclo_inbox_settings first and retain expectedVersion (null only when absent), plus a stable UUID clientRequestId. exact_answers replaces the entire approved answer list; preserve every answer outside the intended edit. It never sends an immediate reply. Enabling automatic replies can cause future replies on enabled accounts, requires explicit owner approval and existing AI consent, and does not enroll any other account. After an uncertain save, read soclo_inbox_settings and reconcile before writing again.

Input Schema

NameRequiredDescriptionDefault
confirmNotrue only after the owner approved the exact text or change. Omit or pass false to get a preview instead: nothing is sent, nothing is saved.
settingsYes
clientRequestIdYes
expectedVersionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / settings / properties / auto_faq
      Added value: +{
+  "description": "Answer simple questions itself using the owner's saved answers. Defaults on; does not turn AI Inbox on.",
+  "type": "boolean"
+}
    • addedInput schema / properties / settings / properties / private_buying
      Added value: +{
+  "description": "Reply privately to buying comments. Defaults on; does not turn AI Inbox on.",
+  "type": "boolean"
+}
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, and the description goes well beyond them: it discloses the required manage:inbox scope, the preview-vs-write gate on confirm, the fact that exact_answers replaces the entire approved list, that omitting fields leaves them unchanged, and the owner-approval and AI-consent preconditions for enabling. This is exactly the extra context annotations cannot carry.

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 action and the preview-then-confirm gate are front-loaded, and nearly every sentence adds a distinct operational constraint (permissions, versioning, replace semantics, consent, recovery). It is dense and the sentences run long, which slightly hurts scanability, but little is wasted.

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?

There is no output schema, but the description covers what an agent needs: preconditions (read first, manage:inbox, owner approval, AI consent), mutation scope (patch vs full replacement of exact_answers), and post-failure recovery (re-read and reconcile before rewriting). Nothing essential to calling this destructive tool correctly is missing.

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 only 25%, so the description must compensate, and it does for the risky parameters: confirm's preview semantics, expectedVersion (null only when absent), stable UUID clientRequestId, and the replace-vs-omit rule for exact_answers vs other settings. It does not explain kill_switch, instructions, handover_* flags, or the daily_message_cap bounds, though those names plus schema bounds are largely self-explanatory.

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 (preview/save), a specific resource (automatic-reply settings), and clarifies it is an exact patch of that resource. It also names the read sibling soclo_inbox_settings, so the agent can distinguish the write from the read without opening either schema.

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

Usage Guidelines5/5

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

Explicitly prescribes the ordering: preview first, only pass confirm:true after owner approval, read soclo_inbox_settings first to obtain expectedVersion, and re-read and reconcile after an uncertain save. It also states what the tool never does (never sends an immediate reply, does not enroll other accounts), which is exactly the when-not guidance an agent needs.

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

All Soclo 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