Skip to main content
Glama

gif_profile

Read and manage the user's local GIF reaction diary to choose fitting GIFs, switch calibration mode, review learned preferences, or erase stored reactions.

Instructions

What you know about how GIFs land with this user, from their local reaction diary: mode (calibrate = you still ask if a GIF fit; quiet = you only watch reactions, never ask), today's count and pace, what worked per moment, their stated preferences, GIFs already overused. Read it before choosing a GIF to send. Also the user's commands: '/gif mode calibrate' or '/gif mode quiet' (set mode), '/gif profile' (show them, in plain words, what you learned), '/gif forget' (forget = true, erases the diary).

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": "gif_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoSet the mode (the user's command)
forgetNoErase the whole diary (the user's command /gif forget)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.10

TDQS

B3.2/5.0
Behavior1/5

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

The description discloses real behavior (the diary is local, mode changes what the agent does, '/gif forget' erases the diary), which would normally earn credit. However, it states that forget=true 'erases the whole diary,' a destructive data-deletion operation, while annotations declare destructiveHint=false. That is a direct contradiction between the description and the structured safety signal, and an agent relying on the annotation could delete user data believing the call is non-destructive.

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 core guidance ('Read it before choosing a GIF to send') is buried mid-paragraph inside a long run-on sentence dense with parentheses and slash-commands. It is information-rich but unstructured; a lead sentence stating what the call returns, followed by modes and commands, would scan far better.

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?

With no output schema, the description carries the return-value burden and does so well, enumerating mode, count/pace, per-moment hits, preferences, and overused GIFs. For a two-parameter tool this is close to complete; the main gap is that it never resolves the annotation conflict about deleting the diary.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents both parameters and the mode enum, making 3 the baseline. The description does add genuine meaning beyond the schema by explaining what each mode implies for agent behavior (calibrate vs quiet) and tying forget=true to the '/gif forget' command.

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 names the resource concretely: the user's local reaction diary with mode, today's count/pace, what worked per moment, preferences, and overused GIFs. It also states the tool accepts user commands ('/gif mode calibrate', '/gif forget'). What's less clear is the verb — it reads as both a read-profile tool and a command handler, so an agent must infer that the same call does both depending on parameters.

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 an explicit call-to-action ('Read it before choosing a GIF to send'), which situates it ahead of gif_pick/gif_send in the workflow. Mode semantics are spelled out (calibrate = still ask if a GIF fit; quiet = only watch, never ask), giving usable behavioral guidance. It does not distinguish itself from siblings like gif_note or gif_handoff, and there is no explicit when-not guidance.

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