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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the agent knows this is a non-idempotent write. The description adds substantive behavioral context beyond that: the type-specific rules (COUNT takes params: [], NUMBER takes icon and options.withoutGroup) and the 24-column placement grid. It doesn't discuss permissions or dashboardId validity, but against the annotation baseline this is solid added value.

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?

A single front-loaded paragraph that moves from the action to the payload shape to placement, with every clause carrying concrete spec information. It is dense and heavy on inline code, but no sentence is redundant.

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?

With 9 parameters, deep nesting, and an output schema present, the description covers the hard parts (series, groupBy, options) but leaves `filter` – which controls which rows the whole widget counts – and `subGroup` entirely undocumented, plus no mention of the required dashboardId. Adequate for the common chart case, incomplete for filtered/sub-grouped widgets.

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 coverage is only 33%, so the description carries real weight and largely delivers: it gives literal payload examples for series.fn.functionTypes/params, the PROPERTY groupBy shape, options.position, and icon. It omits the `filter` parameter, `subGroup`, `name`, and `dashboardId`, and its type list drops COMBO which the schema enum allows – a minor inconsistency, not a contradiction.

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?

Opens with a concrete verb+resource: 'Add a chart or number to a dashboard', which is clearly distinct from widget.update / widget.delete. It does not explicitly name a sibling or state what happens if the widget already exists, but the create semantics are unambiguous.

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?

The phrase 'in the shape steps.draft uses' hints at the intended workflow context, but there is no explicit when-to-use or when-not-to-use guidance and no routing to widget.update for modification. Usage is only implied.

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