Get Better Widget Guide

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it describes the shape of the response (a scoped build brief fused with stable design rules), the intake loop ('Pass every known intake field. If the response lists missing items, ask only for those items and call the tool again before implementation'), the delegation chain, and an explicit non-promise ('It never promises search rankings'). These are workflow facts an agent cannot infer from the schema.

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?

Purpose is front-loaded in sentence one and the structure follows a logical progression: trigger, intake loop, page-family branch, response contents. Some redundancy exists, notably re-explaining 'page family' as CSV/database rows when the format parameter's schema already says exactly that, but the length is defensible for a 14-parameter planning tool.

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 14-parameter, zero-required-parameter tool with no output schema, the description supplies what is missing elsewhere: what the response contains, how to recover from missing intake fields, and which sibling calls follow. An agent can call this correctly and act on the result without further inference.

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 per-parameter meaning is already documented; the description adds the cross-parameter conditional that dataSource, urlPattern, and uniqueValue are page-family-only, and that passing format 'page-family' changes what the brief covers (data source, template, slugs, sitemap, canonicals). That conditional relationship is real added meaning, though individual parameters like transformation or visualContext are not elaborated in prose.

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 opens with a specific verb pair and resource: 'Plan and build a Better Widget for an article, guide, or landing page, or a page family built from a dataset.' It immediately establishes two distinct output shapes (single widget vs. page family) and is clearly separable from siblings like get-ui-principle or get-review-rules, which it references rather than overlaps with.

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?

Explicit triggering conditions are given ('Call this whenever the user asks for a calculator, estimator, converter, generator, quiz, checklist, SEO widget, or interactive article tool') plus the branch selector ('For a page family... pass format "page-family"'). It also names the alternatives it delegates to (get-ui-principle, get-ux-principle) and the mandatory downstream steps (get-review-rules, check-comprehension), so sequencing is unambiguous.

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