Skip to main content
Glama

gif_pick

Captures the GIF a user picks in the GIF tray, prepares it for sending, and records it to their diary for later preference learning.

Instructions

For GIF pickers (the gifmate tray): prepares the GIF the USER picked to send you, and writes it to their diary. Never call it yourself: to send a GIF, use gif_send.

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_pick"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNoOr the GIF itself, base64 (a GIF pasted in the chat)
titleNoThe GIF's title
sourceNoGIF URL or local path
recent_pasteNoOr the GIF just pasted in Claude Code, from its session images

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.10

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description discloses the persistent side effect — a write to the user's diary — and clarifies that the tool is host/UI-triggered rather than agent-triggered. It does not say whether the diary write is reversible or what happens on repeat picks, so it stops short of full behavioral disclosure.

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

Conciseness5/5

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

Two short sentences with no filler; the 'what it does' comes first and the hard constraint ('never call it yourself') plus redirect immediately follow.

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 tool the agent is explicitly told not to invoke, purpose, trigger context, side effect, and the correct alternative are all covered, and the schema handles the inputs. Return behavior is not described, but with no output schema and no agent-side invocation that is a minor gap.

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 description coverage is 100%, so all four parameters (data, title, source, recent_paste) are already documented, including the base64 and pasted-image alternatives. The description adds no further parameter meaning beyond the vague notion of 'the GIF the USER picked', so the baseline of 3 applies.

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 a concrete actor and action: it takes the GIF the USER selected in the gifmate tray and writes it to their diary. That is specific enough to distinguish it from gif_send, though the phrasing 'prepares the GIF ... to send you' is slightly unusual and takes a second read to parse.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit prohibition ('Never call it yourself') plus the correct alternative ('to send a GIF, use gif_send'), which is exactly the routing an agent needs. No inference required about when this tool applies versus the sibling.

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