Get Inspiration

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds real behavioral context: it delivers actual payloads (images, HTML source, screenshot sets) into context, matching is by flow-name best match rather than exact lookup, html-flows is web-only, and `context` is analytics-only with no effect on results. It does not say what happens when nothing matches or how large the payload can be.

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 the value proposition, then a scannable per-type bullet list, then the when-to-use line. Well structured with little filler, though the bullets partially restate parameter descriptions already at 100% schema coverage.

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?

Six parameters, one required, full schema coverage, no output schema — and the description does describe what comes back (product screens as images, rebuilt HTML flows, App Store screenshot sets). Missing only edge-case behavior (no-match results, payload size), which is minor for a read-only retrieval 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 coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: `query` is matched against flow names and should be a few words like "settings" or "invite team" (i.e., keyword matching, not semantic search), `platform` is only relevant for app-screens, and `category` only for app-store-screenshots. That per-type relevance mapping is genuinely useful routing information not obvious from the flat schema.

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 and resource: send real reference designs from a named library (Better Design), for the stated goal of studying how shipped products solved the same problem. This clearly distinguishes it from the many sibling guidance tools (get-widget-guide, get-ux-principle, etc.), which return principles rather than real designs.

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?

Usage timing is explicit: 'Use it before a redesign or a new screen,' with the follow-up action ('then design the user's own screen from what the references do well'). It also gives per-type selection conditions (app-screens vs html-flows vs app-store-screenshots, with html-flows restricted to web apps). It stops short of stating when NOT to use it or naming a specific sibling alternative.

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