Skip to main content
Glama

Add the business's pictures

add_pictures

Adds the business's own pictures: product shots, the products in use (lifestyle), brand pictures, and posts it already published (use post: their look, finish, light and palette is what Marsell's new pictures share, never their subject or words). Each one from a public https url or its bytes (data_base64), with a caption saying what it shows, its use, and the product's name when it shows one. A picture of one of the business's own characters (named first with add_characters) gives character and the look it shows, and it becomes that character in that look, kept exactly as pictured; a picture of its own place (named with add_places) gives place. Send clean pictures of each look (a character sheet or a render on a plain ground), not frames where it is small or among other things. Say when a screen of its product shows a demo, a sample or a client's brand rather than the business's own. PNG, JPEG or WebP (an SVG is drawn to a PNG). They become the project's pictures, which Marsell reads after the owner confirms and uses as references for the pictures it makes. As many as the business has. For files on the agent's own machine, get_upload_link gives an address to send them to from your shell, so nothing big passes through your messages.

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": {
      "pictures": "<pictures>"
    },
    "name": "add_pictures"
  }
}

Input Schema

NameRequiredDescriptionDefault
picturesYesOne or more pictures, each from a url or its bytes, with its caption.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only cover mutation and open-world flags; the description adds substantial behaviour: pictures become project assets, Marsell reads them after owner confirmation and reuses them as references, character/place images are permanently bound to that entity 'kept exactly as pictured', and concrete limits are given (8 MB per URL, ~4 MB base64 per message, PNG/JPEG/WebP with SVG auto-converted).

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 purpose is front-loaded in the first sentence, and most sentences carry unique information, but the middle is a dense run-on with awkward nested parentheticals (e.g. 'use post: their look, finish, light and palette is what Marsell's new pictures share…'). A reordered, bulleted structure would deliver the same content with less parsing effort.

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 nested array-of-objects tool with eight per-item fields, association rules, size limits and an upload pathway, the description is largely sufficient with no output schema to lean on. It leaves minor gaps: what happens on rejection/duplicate uploads, and what the 'other' use value means.

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 prose genuinely enriches several fields: it explains that a 'post' is kept for its look, finish, light and palette and never its subject or words, and it clarifies the character-plus-look pairing and that a place picture 'joins that place'. That is meaning the schema blurbs do not carry.

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 opens with a specific verb and resource — 'Adds the business's own pictures' — then enumerates the exact subtypes (product, lifestyle, brand, posts). It distinguishes itself from neighbours by naming add_characters, add_places, add_products and get_upload_link as prerequisites and by framing the result as references Marsell later reads, which separates it from make_pictures.

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 clear usage conditions: name a character with add_characters first, a place with add_places, a product via add_products, and use get_upload_link when files live on the agent's own machine. It also tells the agent which pictures to send ('clean pictures of each look… not frames where it is small') and to flag demo/sample/client-brand screens. It never states an explicit 'do not use this for X' exclusion, so it stops just short of the top score.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.