advise

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

With no annotations, the description carries the full burden and does substantial work: it discloses that the model runs locally, that it 'sees only what you pass' (so evidence must be included explicitly), that media must be base64 data: URIs rather than URLs or paths, and what each question type returns. It omits cost/latency/rate-limit and any failure-mode behavior, keeping it out of the top band.

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

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

Purpose is front-loaded in the first sentence, followed by role, usage contexts, input requirements, and per-type outputs in a logical order. Dense but nearly every sentence carries information; the 'ember advises; you decide' restatement is the only mildly redundant line.

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

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

An output schema exists, so return values need not be described, yet the description helpfully summarizes the shape per question type. Combined with the media-encoding constraints and evidence-inclusion warning, an agent has enough to call this correctly; only edge cases (model selection, media_kwargs tuning) are left entirely to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is reported as 0%, so the description must compensate, and it does: it explains what belongs in `state` ('include every piece of evidence the call depends on'), how `images`/`videos` must be supplied, and the semantics of the `choice`/`score`/`noul` question types. It adds little about `model` or `media_kwargs`, but the core call-shaping parameters are covered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: get a calibrated-probability read on a situation from a named model (ember, Clef-Flash running locally). It also distinguishes the tool's role from the caller's ('ember advises; you decide'), so there is no ambiguity about what the tool returns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Enumerates concrete invocation contexts ('bounded decision points: intent, triage, routing, yes/no gates, and risk, severity, or effort scores'), which is clear when-to-use guidance. It does not state when NOT to use it, and there are no sibling tools to route against, so it falls just short 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.