Skip to main content
Glama

same_energy_task

Read the current step or submit a human choice to advance a SAME-ENERGY task workflow, including final description or authorized image path.

Instructions

Lê a etapa atual ou registra uma escolha humana; não pesquisa nem transmite imagens.

Sem argumentos de edição, acompanha o formulário; wait_seconds aguarda até ready=true. No modo conversacional, use choice com um value de options (ou back) por vez. Na última etapa, passe description OU image_path; image_path requer autorização explícita input_authorized=true. Copia somente a imagem indicada para a entrada local. theme separa a temática das cores em Color e temática. Nenhuma escolha é presumida.

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": {
      "task_id": "<task_id>"
    },
    "name": "same_energy_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
themeNo
choiceNo
task_idYes
image_pathNo
descriptionNo
wait_secondsNo
input_authorizedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false, openWorldHint=false, destructiveHint=false; the description adds meaningful behavior beyond that: image_path requires explicit input_authorized=true, only the indicated image is copied into the local input, and no choice is ever presumed. The filesystem side effect of copying an image is exactly the kind of context annotations do not convey. It still doesn't describe what a call returns or what happens on invalid choice values.

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?

Information is front-loaded and grouped by topic (mode, last step, theme), with no filler sentences. However, several clauses are compressed to the point of ambiguity — 'theme separa a temática das cores em Color e temática' is nearly unparseable, and the 'Sem argumentos de edição' clause forces the reader to infer which parameters count as editing arguments.

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 7-parameter, stateful, step-driven tool with no output schema and 0% schema coverage, the description covers the mutation behavior, the authorization requirement, the side effect, and the parameter interaction rules. Gaps remain around what task_id identifies and what the agent should expect back from a read call, but the calling contract is substantially complete.

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 description coverage is 0%, so the description carries the full burden, and it explains choice (a value from options, or 'back'), wait_seconds (blocks until ready=true), description vs image_path (mutually exclusive on the last step), input_authorized (prerequisite for image_path), and theme (separates theming from Color/theme). Only task_id, the required parameter, is left unexplained, and the theme sentence is hard to parse.

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 opening sentence gives a specific dual verb-plus-resource: it reads the current step or registers a human choice, and it explicitly excludes searching and image transmission. This lets an agent distinguish it from image/search siblings. It does not name a concrete alternative tool by name, which keeps it short of a 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?

Strong conditional guidance: with no editing arguments it follows the form, wait_seconds is used to block until ready=true, choice is used one value at a time in conversational mode (including 'back'), and on the last step you pass description OR image_path. It does not say when to prefer this over same_energy_status or same_energy_check_updates, so routing against those siblings is left implicit.

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