Skip to main content
Glama

rate_handoff

Record an engineer's judgment of a session handoff: track retained constraints and decisions, duplicate investigation, wrong next steps, re-explanation, and whether retrieval changed the outcome.

Instructions

Record the ENGINEER's judgment of one handoff (a fresh session that picked up a thread) — never your own score. Ask them, then pass what they said: constraints_retained / decisions_retained (did the new session honour them without being told again), duplicate_investigation (re-did finished work), wrong_next_step, re_explained (how many times they had to re-explain past context), retrieval_used / retrieval_changed_action (was a past thread searched, and did it change what happened). Leave unknown fields out.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "rate_handoff"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNo
case_idNo
re_explainedNo
retrieval_usedNo
wrong_next_stepNo
decisions_retainedNo
constraints_retainedNo
duplicate_investigationNo
retrieval_changed_actionNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It usefully discloses that the data must come from the engineer rather than the agent's own assessment, and that unknown fields should be omitted (partial writes). It does not say whether repeated calls overwrite a prior rating, what permissions are needed, or what happens if case_id is absent.

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 critical constraint (record the engineer's judgment, not your own) is front-loaded, and the field glossary is dense with no filler. The single em-dash-chained sentence is long and slightly run-on, which costs a point on readability.

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?

An output schema exists, so return values need no explanation, and the 'leave unknown fields out' instruction covers the all-optional parameter set. The only gap is the unexplained case_id, which an agent needs in order to know which handoff is being rated.

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 0%, so the description must compensate, and it largely does: it explains the meaning of seven of the nine parameters, including non-obvious ones like 'duplicate_investigation (re-did finished work)' and 're_explained (how many times they had to re-explain past context)'. Only 'note' and 'case_id' are left unexplained.

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 ('Record the ENGINEER's judgment of one handoff') and immediately defines the resource ('a fresh session that picked up a thread'). The emphatic 'never your own score' distinguishes it from the sibling 'handoff' tool, which creates rather than rates a handoff.

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?

Gives clear procedural guidance: 'Ask them, then pass what they said' and 'Leave unknown fields out', which tells the agent both the trigger and how to handle partial data. It does not explicitly name an alternative tool or state when not to call it, so it falls short of a 5.

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