Skip to main content
Glama

gif_search

Search GIPHY for a reaction GIF by feeling or current trend, then send the chosen result with gif_send at a moment that fits the conversation.

Instructions

Search GIPHY for a reaction GIF to send the user, then send it with gif_send on its gif URL. Follow gifmate's rules: only at a moment that earns it (a hard-won win, good news, a kickoff, a warm sign-off), never when something failed or the user is stressed, at most one per reply and not two replies in a row. Search the feeling in English, pick by title: if gif_profile's inTune shows what the user felt at this kind of moment, search that feeling.

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": {
      "query": "<query>"
    },
    "name": "gif_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYesThe feeling to show, in English or Italian (Italian reaction words are translated). Empty: what is trending.
thumbsNoAlso save a small animated preview (SVG) of each result, for a picker UI

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.10

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare openWorldHint=true and destructiveHint=false, so the description's job is to add context, and it does: it discloses the intended call chain into gif_send via the returned `gif` URL and imposes a per-reply send budget. Gaps remain — it says nothing about result volume, latency, or what the `limit` cap of 12 implies in practice — but the behavioral picture is substantially richer than the annotations alone.

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?

The tool's identity and the hand-off to gif_send are front-loaded, and the constraint list is compact. The sentinel rules are dense but each carries a distinct condition; only the closing inTune sentence feels stacked onto an already long rule block.

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 still conveys the key return detail an agent needs — results carry a `gif` URL to pass onward — and the `thumbs` flag's side effect is covered by the schema. What's missing is any statement of how many candidates come back or how to choose among them beyond "pick by title", which for a subjective selection tool is a meaningful residual 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 coverage is 67%, so the schema already documents all three parameters including default/max on `limit` and the picker-UI purpose of `thumbs`. The description reinforces the query semantics ("Search the feeling in English", plus the Italian-handling and trending-on-empty behavior found in the schema) but adds no new constraint the schema lacks.

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 ("Search GIPHY for a reaction GIF") and explicitly distinguishes itself from the sibling that performs the delivery ("then send it with gif_send on its `gif` URL"). An agent can tell this is the retrieval half of the pair without opening any schema.

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 explicit positive triggers (a hard-won win, good news, a kickoff, a warm sign-off), explicit exclusions (never when something failed or the user is stressed), hard frequency caps (at most one per reply, not two replies in a row), and a named alternative source of guidance (gif_profile's inTune). This is a complete when/when-not/where-else policy.

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