Skip to main content
Glama

Get sentiment report

get_sentiment_report
Read-onlyIdempotent

Customer sentiment over the last N days (Reports -> Sentiment), one conversation at a time. summary: conversations read (unread = could not be read, left out of rates), ending_negative_rate, net_sentiment (% closing positive minus % closing negative, -100..100), opened_negative and recovery_rate (of the conversations that opened negative, how many closed neutral or positive), worsened_rate, attention_now. matrix: opening -> closing counts. breakdown.agents credits each conversation to whoever handled it at its last burst (handler bot = the AI agent); recovery_rate is the fair measure of an agent, since it does not depend on how many negative conversations they inherited, and low_sample marks a row with too few conversations to judge. Also frustration by inbox (levels: tranquilo, molesto, frustrado, hostil in Spanish), flags (asked for a person, churn risk, abusive language, minutes until an agent replied), quality (CSAT by closing sentiment, response and resolution times by opening sentiment) and the conversations that need attention now (attention: the 10 most recently active; summary.attention_now is the total). Sentiment is recorded only while it runs in enforce mode, so all zeros usually means it is off or still in shadow. The product calls it "sentimiento" in Spanish. channel=voice keeps the AI phone calls, channel=chat the rest.

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": "get_sentiment_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoHow many calendar days to measure, today included (7 = today and the 6 before; this month = today's day of the month). Defaults to 30.
fieldsNoOptional: return only these fields of each record.
channelNoOnly phone calls to AI lines (voice) or only chat (chat). Omit for both.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / channel
      Added value: +{
      +  "description": "Only phone calls to AI lines (voice) or only chat (chat). Omit for both.",
      +  "enum": [
      +    "chat",
      +    "voice"
      +  ],
      +  "type": "string"
      +}
  2. First observed

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 and closed-world, so the safety profile is covered. The description goes well beyond that with real behavioral context: sentiment is only recorded in enforce mode, unread conversations are excluded from rates, low_sample flags unreliable rows, and attention_now is a total while attention returns only the 10 most recently active. It stops short of describing pagination or the response envelope.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first sentence, and with no output schema the metric explanations do earn their place. However, it is delivered as one dense run-on paragraph with no separation between summary, matrix, breakdown, frustration, flags and quality, making it hard to scan and easy to mis-parse.

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?

For a report tool with no output schema, the description carries the return-value burden well, explaining every section, the rate definitions, the agent attribution logic, and the enforce-mode caveat. It is nearly complete, missing only how results are ordered or bounded beyond the attention list.

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 and the schema already documents days and fields precisely. The description still adds meaning the schema lacks, notably the chat/voice split for channel and the interpretation of the returned metrics. One inconsistency: the description refers to 'low_sample' while the schema enum value is 'min_sample', which could confuse an agent selecting fields.

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?

The opening sentence names a specific verb and resource ('Customer sentiment over the last N days ... Reports -> Sentiment') and ties it to a concrete product location, so the agent knows exactly what is returned. It does not name any sibling report tool, so differentiation from get_agent_report, get_team_report or list_sentiment_conversations is left to inference; the phrase 'one conversation at a time' also reads ambiguously.

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?

There is no explicit statement of when to pick this over the sibling report tools, so selection is implied by the resource name alone. It does provide useful operational guidance for the channel parameter ('channel=voice keeps the AI phone calls, channel=chat the rest') and a diagnostic rule that all-zero results usually mean sentiment is off or in shadow mode.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources