Generate build-contract bundle

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

Annotations already declare read-only/idempotent/non-destructive, and the description adds substantial context beyond them: it fetches the URL and extracts CSS/:root tokens without a browser, caches results ~24h per URL, reports realistic bundle size ranges (~7 KB to ~530 KB), and specifies that an unknown part name errors with the valid list. No claim conflicts with readOnlyHint=true — generation is local, not a remote mutation.

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?

Front-loaded with purpose, outputs, and exclusions before the operational detail, which is good ordering. It loses a point for redundancy — the valid parts list (tokens, lintConfig, agentRules, componentContract, antiPatterns, designMd) is repeated verbatim twice, and the response-shape sentence is restated with a 'with parts' addendum.

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 compensates fully by spelling out the return shape ({ ok, url, score, grade, pass, warn, fail, total, tokensExtracted, bundle, checks[] }) and the parts-modified variant. Combined with caching, size expectations, and error behavior, nothing an agent needs to call this correctly is missing.

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 the baseline is 3, but the description adds real semantics: parts is order-preserving, the response still keeps score/grade/counts/checks while bundle holds only the named files, and omitting parts returns everything. The url default is already in the schema, so this is additive rather than merely restated.

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?

States a specific verb+resource ('Generate a frozen build-contract bundle') and enumerates the six concrete artifacts emitted, so an agent knows exactly what comes back. It also explicitly names the siblings it is not (designesy_score, designesy_tokens_score, designesy_drift_score), making it easy to distinguish from the other 16 designesy tools.

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?

Contains an explicit 'Use this when...' clause plus a dedicated 'When NOT to use' section that routes to three named alternative tools by purpose. It also explains how to narrow output via parts, which is usage guidance for invocation as well.

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