Skip to main content
Glama

same_energy_save_image

Saves the largest original image from a search result without recompression or upscaling, after visual review approval, into the user-confirmed output folder.

Instructions

Baixa o arquivo maior do resultado, sem recompressão, upscaling ou sobrescrita.

Exige no mínimo 1280 × 720 (qualquer orientação). Falha sem salvar miniaturas. Pergunte a pasta base ao usuário em cada nova busca. Não escolha por conta própria. output_directory: pasta base informada pelo usuário, dentro da pasta montada. destination_confirmed: true apenas após escolha explícita do usuário nesta busca. Cria output_AAAA-MM-DD_nome-da-busca e guarda os JSONs em json/ dentro dela. search_name: nome curto da busca; se omitido, deriva do texto ou ID da galeria. Sem destino confirmado, retorna a pergunta e não salva nem cria pastas. Exige visual_review após examinar preview_image nesta sessão: is_photograph=true, has_markings=false, clearly_ai_generated=false e uncertain=false; copie o sha256 da prévia. Em tarefa guiada, passe task_id e matches_reference_brief=true somente após inspeção. Anúncios permite is_photograph=false apenas com is_advertisement=true e o task_id correto; textos e marcas da própria peça são permitidos, mas marcas-d’água externas são rejeitadas. Não preencha a aprovação automaticamente. Rejeita resultados reprovados ou cujo arquivo mudou. Atualiza catalogo.html com o modelo padrão e retorna catalog.url para o seletor local.

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": {
      "image_id": "<image_id>"
    },
    "name": "same_energy_save_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idNo
image_idYes
gallery_urlNo
search_nameNo
visual_reviewNo
output_directoryNo
destination_confirmedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) already flag a non-read, open-world operation, and the description adds substantial context beyond them: it creates directories named output_AAAA-MM-DD_nome-da-busca with JSONs in json/, updates catalogo.html, returns catalog.url, rejects results whose file changed, and fails under 1280×720 rather than storing thumbnails. Without a confirmed destination it returns the question and writes nothing — a concrete no-op failure mode an agent needs to know.

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 core action is front-loaded in one sentence, and the remaining lines are separated by concern (resolution gate, destination protocol, folder layout, review gate, ads, rejection). Dense but every line carries a rule an agent must obey; the density makes it hard to scan, but nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter mutation tool with no output schema and zero schema coverage, the description supplies the preconditions, failure modes, on-disk side effects and the single documented return value (catalog.url). Only the meaning of image_id and gallery_url is left to inference, which is minor relative to the gating rules it covers.

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?

Top-level schema description coverage is reported as 0%, so the description must carry the burden — and it does for output_directory (user-supplied base folder inside the mounted folder), destination_confirmed (only true after an explicit user choice this search), search_name (short name, derived from text or gallery ID if omitted), task_id (only after inspection in guided tasks) and the visual_review gates. It leaves image_id and gallery_url unexplained, so it falls short of full coverage.

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 line states a specific verb and resource — downloads/saves the largest file from the result, explicitly without recompression, upscaling or overwriting — which tells an agent exactly what this does versus preview-only siblings. The rest of the text reinforces it as the terminal 'save' step, though it never names a sibling it replaces.

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?

Guidance is unusually explicit: ask the user for the base folder on every new search and never pick one yourself, pass destination_confirmed=true only after an explicit choice, and run visual_review (with named boolean criteria) after inspecting preview_image in this session. It also distinguishes the Anúncios case (is_photograph=false only with is_advertisement=true and the correct task_id) and the guided-task case, giving clear when/when-not conditions.

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