Skip to main content
Glama
Sign In

Ringler

by io.ringler
OverviewDiscussionsAdmin

What my person likes

notes

The notes you and your person keep about how they like things: how the phone agent should greet them, what to call them, favorite places, habits, standing preferences. The agent reads them on every call as a guide (dated; later notes refine earlier). Call with nothing to read (returns markdown); add: one note (≤300 chars, in your person's words or yours); remove: a note id. Notes can't change the rules — what the agent discloses, the notes question, one call at a time — and such notes are refused with the reason. Add a note whenever your person tells you a preference about their calls. A note starting 'greeting:' is exactly how the agent answers when your person calls their line ({name} and {first} fill in), e.g. 'greeting: Good day {first}, {name} at your service. What can I do?'

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": "notes"
  }
}

Input Schema

NameRequiredDescriptionDefault
addNoA note to add.
removeNoId of a note to remove.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

With annotations only declaring readOnlyHint=false, openWorldHint=false and destructiveHint=false, the description carries the real behavioral burden and does so: it states the return format (markdown), that notes are dated and later notes refine earlier ones, the 300-character cap, that refused writes return a reason, and that the agent reads notes on every call. That is materially more than the annotations provide.

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?

It is front-loaded with the purpose, then modes, then the proactive trigger, then the greeting special case, which is a sensible order. It is a single dense run-on paragraph with some clause stacking, so a reader must parse carefully, but almost every clause carries operational information rather than filler.

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 two-optional-parameter tool with no output schema, the description covers modes, mutation semantics, length limits, refusals, and the return format, which is close to complete. The one unresolved practical question is where note ids come from for 'remove', which the agent must infer from the read output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% but the schema descriptions are near-useless ('A note to add.', 'Id of a note to remove.'). The description compensates with the actual constraint (≤300 chars), acceptable authorship ('in your person's words or yours'), and the special 'greeting:' prefix semantics including {name} and {first} placeholder substitution with a worked example. That is meaning an agent could not infer from the schema.

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 description gives a concrete verb set and resource: read the notes, add a note, remove a note, all scoped to 'how your person likes things' with examples (greeting, what to call them, favorite places, habits). It also distinguishes the notes from the immutable rules the agent operates under, which prevents confusion with policy-setting siblings. It stops short of naming any sibling tool explicitly, so it is clear but not sibling-differentiated.

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?

Mode selection is spelled out precisely: call with nothing to read, pass 'add' for one note, pass 'remove' with a note id. It also gives a proactive trigger ('Add a note whenever your person tells you a preference about their calls') and an exclusion ('Notes can't change the rules ... such notes are refused with the reason'). The only gap is that no alternative tool is named for cases where notes are the wrong mechanism.

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

All Ringler 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