explain_visual

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

With no annotations, the description carries the burden alone; it does establish non-mutating intent via 'Explain' and the explicit non-modification clause. However, it never says whether the 'exact DAX query' is actually executed against the model (and thus has cost/latency/side effects), what happens when the spec is invalid, or what authorization the connection requires.

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?

Two tight sentences with the primary output content front-loaded and the scope caveat second; nothing reads as filler. Density is high but each element (spec, bindings, ECharts option, DAX query) earns its place.

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?

There is no output schema, and the description partly compensates by listing what the explanation contains. But for a tool with nested objects, a UUID connection reference, and a row cap, it omits the meaning of two parameters and says nothing about failure modes or response structure.

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 0% with four parameters, two nested, so the description must compensate and largely does not. It covers only 'spec' and 'bindings' at a name level; 'connectionId' (which model the DAX targets) and 'maxRows' (a sampling bound up to 10000) are never mentioned, leaving half the input surface unexplained anywhere.

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?

The description uses a specific verb ('Explain') and enumerates exactly what gets explained: the spec, field bindings, resolved empty-data ECharts option, and exact DAX query. The closing negative clause ('Does not inspect or modify native visuals or model objects') carves out scope against read_visual/update_visual, though it never names the sibling that should be used for those cases.

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?

'before preview or commit' gives concrete ordering guidance that ties this tool to specific siblings in the workflow. The exclusion of native visuals and model objects provides when-not guidance, but no alternative tool is named for those scenarios.

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