Skip to main content
Glama
Pickle Air MCP

Pickle Air MCP

pickle_download_image

Save the newest image an agent sent in the allowed chat to the local download folder as a PNG using the app's Save photo button, without sending a message.

Instructions

Save the newest picture the agent sent in the allowed chat (reply_images > 0, shown as [image] in the reply) to the fixed local download directory as pickle-image-.png, using the app's own Save photo button. Does not send a message. File is untrusted; view it yourself, never execute it.

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": {
      "agent": "<agent>"
    },
    "name": "pickle_download_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotation already declares non-readOnly, non-idempotent, non-destructive, open-world, so the description is not the only source of safety context. It still adds real value: the write target is a fixed local download directory, the generated filename uses a timestamp, the write goes through the app's own Save photo button, no message is sent, and the downloaded file is flagged as untrusted and must not be executed.

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?

Three tight sentences: action and target first, the no-message constraint second, the untrusted-file warning last. Every sentence carries information, though the reply_images/[image] parenthetical is slightly dense.

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 simple single-parameter download tool with no output schema, the description covers the trigger, the destination, the filename pattern, the side effect, and a security caveat. The one gap is that the 'fixed local download directory' is never given as a concrete path, so the agent cannot know where the file actually lands.

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?

There is one parameter with 0% schema description coverage, so ideally the description would explain it. The 'agent' parameter is a single-value enum (only 'agent' allowed), which is nearly self-explanatory, but the description never mentions it or clarifies what value to pass, leaving only a minor gap.

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 precise verb and resource: save the newest picture the agent sent in the allowed chat to a fixed local directory as pickle-image-<time>.png. It is very specific about scope (newest only, image replies where reply_images > 0, shown as [image]), but it never names a sibling such as pickle_download, so differentiation is inferred rather than stated.

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

Usage Guidelines3/5

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

It gives an implicit trigger (a reply containing [image] / reply_images > 0) and one negative constraint ('Does not send a message'), which helps separate it from message-sending siblings like pickle_ask. It does not explicitly state when to prefer this over the general pickle_download or what to do if no image exists.

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