Skip to main content
Glama
Sign In

Invoke Human Tool

by com.invokehumantool
OverviewDiscussionsAdmin

Read handoff history

get_handoff_history
Read-onlyIdempotent

Revisions of a handoff this key can see. since_revision returns rows after that number. limit defaults to 50 and maxes at 100. Shared revisions are visible to accepted seats. Per-seat revisions are visible to that seat and the sender. Only-for-me revisions are visible to the seat, and to the sender only when share_with_agent was set on that write.

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": {
      "id": "<id>"
    },
    "name": "get_handoff_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesHandoff id, hnd_...
limitNo
since_revisionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the description earns credit for what they cannot convey: the three-tier visibility model (shared, per-seat, only-for-me) and the share_with_agent condition that exposes only-for-me rows to the sender. That is genuinely non-obvious access-control behavior. It does not mention result ordering or what a 'revision' row contains.

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 scope, then pagination mechanics, then visibility rules in increasing specificity. Every sentence carries information, though the visibility sentences are telegraphic and require familiarity with the domain terms.

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?

No output schema exists, so the description must cover return shape, and it only says 'rows' without naming revision fields, ordering, or whether the response includes a next-cursor. For a paginated history read that omission leaves the agent guessing about how to continue iterating.

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 only 33%, and the description compensates well: since_revision is defined as an exclusive cursor on revision numbers, limit gets a default (50) and a cap (100). The required id parameter is left to the schema, which already describes it as 'hnd_...', so the gap is minor.

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?

Opens with a specific resource and scope: 'Revisions of a handoff this key can see,' which distinguishes it from siblings like get_handoff_status and get_handoff_result that return current state rather than history. It stops just short of a clean verb ('List revisions of...'), which costs it the top mark.

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?

Usage is only implied by the resource name and the since_revision sentence. There is no explicit 'use this when you need the audit trail' versus 'use get_handoff_status for current state' routing, nor any guidance on when pagination via since_revision is needed.

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

All Invoke Human Tool 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