Skip to main content
Glama

CarlNotes

Read updates

read_updates

Read the user's CarlNotes updates: the unread findings Carl would read next across the topics they follow, or on one topic, trimmed to 5, 15, or 30 minutes of reading. Every finding it returns counts as read, so the next call moves on. Use it for requests like what's new, catch me up, update me, or what's new on a topic. Call it once for each time the user asks.

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": "read_updates"
  }
}

Input Schema

NameRequiredDescriptionDefault
minutesNoHow many minutes of updates to read: 5, 15, or 30. Leave it out for 15.
topic_idNoOne topic to read updates on. Leave it out for every topic the user follows.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

The description carries the critical behavior the annotations cannot: "Every finding it returns counts as read, so the next call moves on." That explains the otherwise surprising readOnlyHint=false and warns the agent that invoking the tool advances state irreversibly. The once-per-request rule adds further operational context beyond the annotation set.

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, front-loaded with purpose before usage and the state-advancing caveat. Slightly repetitive in restating "what's new" in the trigger list, but no filler sentences that fail to earn their place.

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 2-parameter, fully documented, non-destructive tool with no output schema, the description covers purpose, scope, defaults, triggers, and the key side effect. The only gap is not hinting at the return shape or ordering of findings, which is minor given the tool's simplicity.

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, but the description adds real meaning: "minutes" is a reading-time budget ("trimmed to 5, 15, or 30 minutes of reading"), not a result count, and "topic_id" scopes to one topic versus all followed topics. This clarifies the enum's intent beyond the schema text.

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 names a specific verb and resource ("Read the user's CarlNotes updates") and immediately scopes the resource: unread findings across followed topics, or on a single topic, trimmed by reading time. That scope plus the consumption behavior distinguishes it from siblings like read_topic_feed or read_activity without needing to name them.

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?

It gives concrete trigger phrases ("what's new, catch me up, update me, what's new on a topic") and a cadence rule ("Call it once for each time the user asks") that discourages looping. It stops short of naming when NOT to use it or which sibling to pick instead, so it gets a 4 rather than a 5.

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.