ember

advise

Get calibrated probability judgments for yes/no, named-choice, or ordered-score questions about a situation, with optional image or video-frame evidence. Returns one probability per option.

Instructions

Get ember's read on a situation, as calibrated probabilities.

ember (a decision model) advises; you decide. Consult it at bounded decision
points: intent, triage, routing, yes/no gates, and risk, severity, or effort
scores. It sees only what you pass, so include every piece of evidence the call
depends on and attach images or video frames as base64 `data:` URIs in
`images`/`videos` when pixels are the evidence. For 'choice' the answer has the
leading option, its confidence, and full probabilities; for 'score' an expected
score over the ordered criteria; for 'noul' the probability the proposition is true.

Input Schema

Name	Required	Description	Default
`input`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.1.1Oct 13, 2026

changedInput schema / $defs / AdviseInput / properties / model / description

Previous value: -"Model label echoed back in the response."New value: +"Informational label only. The response always reflects the model the server loaded at startup; this field is not used for routing."

First observedv0.1.0Oct 3, 2026

TDQS

A4/5.0

Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does well: it discloses that ember 'sees only what you pass,' that evidence must be attached as base64 data: URIs, and how each question type formats its answer. It omits latency/cost/rate-limit characteristics and failure modes, so not a 5.

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?

Front-loaded verb+resource sentence, then a tight paragraph covering usage, evidence handling, and per-type outputs. Slightly dense but every clause adds information; 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?

An output schema exists, so return formatting need not be enumerated beyond the per-type summary the description provides. Combined with usage bounds and evidence rules, it is nearly complete; missing only edge cases like large media or ambiguous question IDs.

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 reported as 0% for the top-level fields, so the description must compensate, and it does: it explains the images/videos data-URI attachment requirement and gives the semantics of each 'type' answer. It leaves questions ID mapping, model label, and media_kwargs largely to the schema, so it is not exhaustive.

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?

States a specific verb (advises) and the resource (ember's calibrated-probability read on a situation), and lists the three answer shapes (choice/score/noul). No siblings exist to differentiate from, so this is as clear as the context demands.

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?

Explicitly names the bounded decision points where it should be consulted (intent, triage, routing, yes/no gates, risk/severity/effort scores) and the framing 'ember advises; you decide.' It stops short of stating when NOT to use it, which keeps it out of the top band.

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

adviseA