Skip to main content
Glama
Vitalini

ebb-ai

by Vitalini
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

recommend_window

Preview the cleanest carbon-aware time to run a task before committing. Returns the optimal window inside a deadline, alternatives, and CO2 savings versus running now.

Instructions

Return the optimal carbon-aware execution window for a task WITHOUT scheduling it. Use this for non-committal planning — to see when the cleanest grid moment falls inside the deadline (and the savings vs running now) before deciding whether to commit via schedule_task. Returns the chosen window, top alternatives, a batch_eligible flag, the grid_source (which feed produced the forecast — 'mock' means synthetic data), and a one-line reasoning string. Read-only; does not touch the task queue.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoOptional vendor model name (e.g. 'claude-sonnet-5'). Affects the reasoning string only.
regionYesElectricity Maps grid zone code (e.g. 'US-CAL-CISO', 'FR') the recommendation reasons over. On hosts that allow omitting it, defaults to the configured region, else a host-timezone guess, else GB.
deadlineYesISO-8601 timestamp (e.g. '2026-05-13T08:00:00-04:00') by which the task must have completed. Must be in the future. Required.
candidatesNoOptional cross-provider routing candidates: 'provider:model' strings (e.g. ['anthropic:claude-haiku-4-5','openai:gpt-6-luna','ollama:llama-3-1-8b']) the caller EXPLICITLY allows. With >= 2 entries the scheduler scores them at the chosen dispatch window on a weighted blend of carbon, cost and latency and dispatches the winner (recording the full scored list on the signed receipt). No silent model swaps — routing only ever picks from this list. Absent or a single entry leaves the provider/model behavior unchanged. Every candidate model must exist in the price table or the task is rejected loudly.
route_weightsNoOptional routing weights {carbon, cost, latency}, non-negative and normalized internally. Default {carbon:0.6, cost:0.3, latency:0.1}. Only used when 'candidates' has >= 2 entries.
carbon_budget_gNoOptional hard cap on estimated grams CO2-equivalent for this task. Windows above the cap are dropped before the cleanest is chosen; if none inside the deadline meets the cap the task fails rather than dispatching to a dirty window.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.16.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it does well: it declares "Read-only; does not touch the task queue," enumerates the returned fields (window, alternatives, batch_eligible, grid_source, reasoning), and warns that grid_source='mock' means synthetic data. It stops short of other operational context such as rate limits, auth requirements, or failure modes outside the carbon cap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads purpose, then usage, then returns, then safety posture in a tight sequence. Every clause carries distinct information (differentiation, return shape, mock-data caveat, read-only guarantee) with no padding.

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 6-parameter tool with nested objects and no output schema, the description compensates by enumerating the return payload. It does not fully cover the routing/candidate behavior, but that is documented in the schema, so the description is adequate though not exhaustive.

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?

Schema description coverage is 100%, so the schema already documents all six parameters in detail, including the routing semantics and defaults. The description adds no additional parameter-level meaning (e.g. syntax or edge cases for candidates/route_weights) beyond what the schema states, so the baseline 3 applies.

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?

States a specific verb+resource ("Return the optimal carbon-aware execution window for a task") and immediately delimits scope with "WITHOUT scheduling it." This directly contrasts with the sibling schedule_task, so an agent can distinguish commit-vs-preview without opening either schema.

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?

Explicitly names the use case ("non-committal planning") and the decision it feeds ("before deciding whether to commit via schedule_task"), routing the agent to the correct sibling. The when-to-use condition is stated rather than inferred.

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

Deploy Server

Other Tools