Skip to main content
Glama
l33tdawg

(S)AGE

by l33tdawg
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Hybrid

sage_message_handoff

Transfer a claimed message's ownership from one MCP session to another using the exact session ID and revision from history, preventing stale or concurrent handoffs from duplicating ownership.

Instructions

Atomically transfer one claimed local or inbound federated message from the claimant_session_id and claim_revision shown by sage_message_history to this MCP session. The expected from_session_id plus from_revision form a revisioned compare-and-swap fence: stale, concurrent, and A→B→A delayed handoffs fail visibly instead of duplicating ownership. Pre-v11.18.24 claims are surfaced as legacy revision 0 and still require this explicit handoff; they are never stolen automatically.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
message_idYes
from_revisionYesExact claim_revision from passive claimed_elsewhere history
from_session_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv11.19.6
    • addedInput schema / properties / from_revision
      Added value: +{
+  "description": "Exact claim_revision from passive claimed_elsewhere history",
+  "minimum": 0,
+  "type": "integer"
+}
    • changedInput schema / required
      Previous value: -[
-  "message_id",
-  "from_session_id"
-]New value: +[
+  "message_id",
+  "from_session_id",
+  "from_revision"
+]
  2. Addedv11.18.22

TDQS

A3.9/5.0
Behavior4/5

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

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It covers atomicity, the revisioned compare-and-swap fence, visible failure on stale/concurrent/delayed handoffs, and legacy revision handling. This is comprehensive and goes beyond a basic statement of purpose, though it does not describe the return value or post-handoff state, which would make it a 5.

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 sentences, each carrying distinct value: the core action, the CAS mechanism, and legacy handling. The main purpose is front-loaded, and technical details are ordered logically. It is slightly verbose but no sentence is wasted.

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?

Given the tool's complexity (CAS, legacy claims) and the absence of annotations and output schema, the description covers the necessary call context: where to find the claim data (sage_message_history), the need for explicit handoff, and the concurrency semantics. It lacks info on response format or side effects, but that is not critical for calling the tool.

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?

Schema coverage is only 33% (only from_revision has a description). The description adds meaning by linking from_session_id and from_revision to the claimant_session_id and claim_revision from sage_message_history, and explaining the revision as a CAS fence. However, message_id is not elaborated beyond the schema's name, so the description does not fully compensate for the low schema coverage.

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 clearly states a specific action: 'Atomically transfer one claimed local or inbound federated message... to this MCP session.' It identifies the resource (claimed message), the source (claimant_session_id and claim_revision from sage_message_history), and the destination (this MCP session). It also distinguishes itself by explaining a CAS fence mechanism, making its purpose unambiguous relative to other message tools.

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?

The description implies when to use the tool (explicit handoff for claimed messages, including legacy claims) but never directly compares it to alternatives like sage_message_send or sage_message_reply. It states that legacy claims are not stolen automatically, implying this tool is required, but it does not explicitly say 'use this when X, use that when Y.' The usage context is stated but exclusions and alternatives are not.

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

Deploy Server

Other Tools