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

With no annotations, the description carries the transparency burden and does well: it discloses the output (locked tokens, contrast-checked, two radii, five-step type scale, usage law, slop rulebook) and the relationship to website directions. It doesn't mention error cases or rate limits, but for a 'get' tool this is sufficient.

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?

The description is front-loaded with the core noun and details, but it's a long block with redundancy (e.g., 'This is how a vibe-coded app stops looking AI-generated' and 'install the theme once and every view the agent builds matches' convey similar ideas). Some marketing language could be trimmed for tighter prose.

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 tool with no output schema, the description thoroughly explains what will be returned (full token system, Tailwind v4 mapping, usage law, rulebook) and the interaction model (browse menu vs. fetch by id). It doesn't cover error handling, but given the tool's scope and good parameter documentation, it is reasonably complete.

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 100%, so baseline is 3. The description adds value beyond the schema by explaining the 'theme' parameter with concrete examples (graphite-ledger, terminal-grade-ui) and clarifying that 'response_format' applies to menu browsing. This enriches the bare schema definitions.

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+resource: 'Get a LOCKED design-token system for application UI', enumerating exact contents (color roles, radii, type scale, spacing, elevation, motion tokens, Tailwind v4 mapping). This clearly distinguishes it from sibling tools like get_design_direction or get_asset_pack by focusing on app-UI theming.

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 description explicitly explains when to call with no theme to browse the menu (free) versus with a theme id to receive the full system. It implies usage for building app UIs and mentions brand DNA with website directions, but does not explicitly name alternative tools or exclusion criteria.

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