Skip to main content
Glama

gif_note

Records reactions, preferences, and missed GIF moments in a local diary so agents learn user humor and send fitting GIFs at the right time.

Instructions

Write to the user's local GIF reaction diary, so you get to know them. Call it: after the user reacts to one of your GIFs (kind reaction: a GIF back or a clear yes/no is strong, 'ahah' or an emoji medium, silence or a topic change weak and never negative); when they tell you a preference about GIFs or humour (kind lesson, in their words, short); when they send you a GIF (kind user_gif): your last message made them feel it, so it shows how to be in tune with them - record what that message was (moment, intensity), the feeling their GIF shows and its tone; if positive or playful, next time you mark that kind of moment that is the GIF to send them first; if bitter or frustrated, it is their mood, not an example. When they say a GIF would have fit: kind missed, with the moment. Labels only: never copy the conversation.

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": {
      "kind": "<kind>"
    },
    "name": "gif_note"
  }
}

Input Schema

NameRequiredDescriptionDefault
gifNoGIF title
kindYes
noteNoA few words: a preference, or what their GIF meant
toneNouser_gif: positive or playful = an example to send them next time; bitter or frustrated (a sour 'this is fine', sarcasm at you) = no example, it tells you to keep your GIFs away for a while
momentNoThe moment the note refers to; for user_gif: what your previous message was
feelingNouser_gif: the feeling their GIF shows, 1-3 English words ('lets go', 'facepalm', 'relief')
outcomeNo
strengthNo
intensityNoordinary or hard_won (it took real effort)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.10

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare this is a local, non-destructive write operation. The description adds meaningful behavioral context: notes are labels only, conversation content must never be copied, and positive versus bitter tones affect future GIF choices.

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, but the description is a dense run-on paragraph with nested parenthetical rules that are hard to parse. Most content is relevant, yet the structure could be much clearer with separated sentences or bullet-like organization.

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?

For a nine-parameter tool with no output schema, the description covers when and how to record notes but omits operational details such as what the tool returns, whether entries append or overwrite, and how stored notes are later retrieved. It is adequate but leaves notable gaps.

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 moderate at 67%, and the description adds substantial meaning for key parameters like kind, tone, moment, feeling, and strength. Some parameters such as gif and outcome receive less explanation, but the description still clarifies the semantic relationships that matter most.

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 clearly states a specific verb and resource: writing to the user's local GIF reaction diary. It distinguishes the tool from sending or searching GIFs by framing it as a note-recording tool, though it does not explicitly name or contrast sibling tools.

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 detailed triggers for each note kind: reactions, preferences, user-sent GIFs, and missed opportunities. It also explains how to classify reaction strength and tone, but does not state when not to use the tool or name alternative tools.

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