Skip to main content
Glama

gif_send

Send a GIF to the user in chat at a fitting moment, passing the GIF source, what it marks, and its intensity so gifmate can apply timing and sensitivity rules.

Instructions

Send a GIF to the user in the chat. Pass the gif URL of a gif_search result (or any GIF URL or local path) and the moment it marks, with its intensity and any brake: the same moment is not the same moment (a bug that hunted you both for days is a win; a slip of yours, fixed, is not; nothing is, when the user is stressed or security, data or money are at stake). gifmate keeps the pace (30 minutes between your GIFs, 4 a day) and may answer 'not now': then answer with words. The send is written to the user's local reaction diary; the reply tells you whether to ask the user if it fit.

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": {
      "source": "<source>",
      "moment": "<moment>",
      "intensity": "<intensity>"
    },
    "name": "gif_send"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNoThe GIF's title (from gif_search)
brakesNoAny that apply: own_fault = the problem was a slip of yours; user_stressed = they are rushed, frustrated, or it is the same bug back again; sensitive = security, data, money, a client, production
momentYesWhat the GIF marks: asked = the user asked you for one; banter = answering their playful GIF
sourceYesGIF URL or local path
captionNoShort caption shown with the GIF
intensityYesordinary, or hard_won: it took real effort (a bug hunted for hours or days, a long refactor done)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.10

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses the rate governor ('30 minutes between your GIFs, 4 a day'), a possible refusal response ('not now'), and a side effect ('written to the user's local reaction diary') plus a follow-up affordance from the reply. These are exactly the operational facts an agent cannot infer from structured data.

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?

Purpose is front-loaded, but the middle clause is a convoluted run-on ('the same moment is not the same moment (a bug that hunted you both for days is a win; a slip of yours, fixed, is not; nothing is, when...)') that largely duplicates the 'brakes' enum semantics. The final clause about the reply is awkwardly phrased and would read better as a separate sentence.

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?

There is no output schema, so the description must carry return behavior, and it does: it explains the possible 'not now' answer and that the reply indicates whether to ask the user if the GIF fit. Given six well-documented parameters and clear annotations, this is nearly complete, though the exact reply shape remains vague.

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 100%, so the baseline is 3, but the description adds genuine meaning: 'source' accepts a gif_search URL, any GIF URL, or a local path, and the 'same moment is not the same moment' example (bug hunted for days = win, own slip fixed = not) effectively teaches when to set the own_fault brake. Values for title and caption are still left entirely to 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 first sentence states a specific verb and resource: 'Send a GIF to the user in the chat.' It also routes the agent to a sibling as the value source ('a gif_search result'), which distinguishes it from search/note siblings. It stops short of explicitly contrasting with gif_pick or gif_handoff, so 4 rather than 5.

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?

The description gives real when-not conditions ('nothing is, when the user is stressed or security, data or money are at stake'), plus a rate-limit clause and a fallback behavior ('may answer not now: then answer with words'). That is concrete routing guidance. It lacks any explicit statement about when a different sibling (e.g. gif_note or gif_pick) should be chosen instead.

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