generate_typography_system

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

With no annotations provided, the description carries the full behavioral burden, and it does substantial work: it discloses the output artifacts, the format selection semantics, the weights syntax per the css2 API, variable-range '..' notation, and legacy comma auto-conversion. The gap is that it does not cover failure modes (e.g., unknown fonts or invalid scale values) or dependencies, though an output schema exists to document return shape. This is solid but not exhaustive.

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?

Four tight sentences, front-loaded with the core purpose and output artifacts before diving into syntax details. There is no fluff or repetition; every sentence adds operational information (deliverables, format values, weight syntax, legacy handling).

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?

Reasonably complete for a tool that has an output schema covering returns: it details formats and weight conventions. But it leaves the 'scale' parameter under-specified — its allowed values presumably come from list_scales, yet no cross-reference is given — and the meaning of body=null and base is not explained. An agent could plausibly pass an invalid scale string. These gaps are notable given 0% schema coverage.

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% across 7 parameters, so the description must compensate — and it only partially does. It adds genuine meaning for 'format' (enumerating css/tailwind/embed/all) and weight syntax (semicolon-separated, '..' ranges, comma auto-conversion), but leaves 'scale' (only a default, 'major-third', with no enumerated options), 'base', and 'body' (null default meaning unspecified) unexplained. It clarifies about a third of the parameters, which is better than nothing but insufficient for the coverage gap.

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?

'Generate a complete typography system from font selection + scale' states a specific verb, resource, and inputs, and names the deliverable (CSS custom properties, Tailwind config, Google Fonts embed HTML). It is unmistakably distinct from the sibling lookup utilities (search_fonts, lookup_font, list_scales, list_pairings), which all retrieve information rather than produce an artifact.

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 implies its position in the workflow — generation after font selection — and enumerates the format dimension (css/tailwind/embed/all), signaling it is the synthesis step rather than a discovery step. However, it never explicitly names siblings or states when to choose this tool over them, nor does it give exclusions or prerequisites (e.g., whether fonts must first come from search_fonts).

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