Material 3 Expressive Reference

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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so the safety profile is fully covered. The description adds a modest behavioral detail — an empty topic lists all topics — and implicitly frames the output as advisory reference content to consult pre-build. It does not disclose how content is returned, whether topic matching is exact, or what happens for an unknown topic; with no output schema, that remains a gap.

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?

One sentence, front-loaded with the topic inventory that is genuinely the most useful information, followed by the usage cue. The keyword enumeration is dense but each term maps to a real capability, so little is wasted; it only loses a point for being a bare list rather than stating scope proportionally.

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?

For a two-optional-parameter reference lookup with no output schema, the agent knows what topics exist, when to invoke it, and how to enumerate everything. The remaining gap is routing against overlapping siblings (component status, Wear OS guide) and any hint about result depth, neither of which is fatal for a read-only knowledge tool.

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 100%, so both parameters are already documented in the schema with examples and the same 'empty to list all' note. The description repeats the empty-topic behavior and adds nothing about the refresh flag or accepted topic forms. Baseline 3 applies when the schema does the work.

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 names the resource (Material 3 Expressive reference) and enumerates the concrete topics it covers — MaterialExpressiveTheme, MotionScheme, ButtonGroup, FloatingToolbar, LoadingIndicator, MaterialShapes, typography, Wear, migration. That gives an agent a strong signal of scope. It is weaker on verb phrasing ("reference" rather than an explicit retrieve/lookup) and overlaps with siblings like android_wearos_guide on the 'Wear' topic, which it does not disambiguate.

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?

"Call before building Compose UI or theming" is explicit timing guidance that tells the agent when this tool belongs in a workflow. "Empty topic lists all" gives a discovery path. However, it offers no exclusions or named alternatives, and the sibling set contains overlapping guides (android_component_status, android_wearos_guide) that are never mentioned.

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