CatchUI

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds return-shape detail (definitions side by side) and a conditional behavior ('plus the catalog's written comparison when one exists'), which is context not present in the structured fields.

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?

Two sentences, front-loaded with purpose and scope, followed by the return behavior. The example list is dense but each item adds disambiguation value; no filler or repetition.

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?

With one fully documented parameter and no output schema, the description covers both input acceptance and what comes back. It does not mention behavior when a supplied pattern is unknown or unmatched, a minor gap for a single-parameter lookup 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 description coverage is 100% and the single parameter's schema entry already documents the 2-4 ids/names/short-descriptions format with examples. The description largely restates that ('Accepts ids, names or short descriptions') without adding new syntax or constraint detail, so the baseline of 3 applies.

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 (compares/diff) and resource (UI patterns) with a precise scope of 2 to 4 items, plus four concrete example pairs. An agent can immediately tell this is a multi-pattern diff rather than a single-pattern lookup, though no sibling tool is named explicitly.

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 phrase 'easily confused UI patterns' and the vs-style examples imply when this tool is appropriate (disambiguating confusable patterns), but there is no explicit when-to-use statement, no when-not-to-use, and no named alternative such as get_ui_pattern.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond them: the output contents, the supported languages, and the intended downstream consumption. It omits any note on rate limits, truncation, or the shape of the returned text.

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?

Two sentences, front-loaded with what is returned and its intended use, then the accepted input forms. No filler and every clause carries information an agent needs to select and call the 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?

With no output schema, the description must carry the return-value burden, and it largely does by enumerating the prompt contents and language options. It never says whether the result is one combined string, a per-pattern array, or how the six-pattern case is structured, which is a modest remaining gap for a no-output-schema 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 real meaning the schema does not: inputs may be ids, names, or short descriptions (fuzzy resolution), and the 1–6 bound is restated in prose with examples. It does not explain how ambiguous descriptions are resolved or what happens on a miss.

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: returns 'ready-to-use implementation instructions for 1 to 6 UI patterns', and enumerates the payload (what to build, where it sits, states, accessibility). The framing 'for pasting into an AI coding tool such as Claude Code or Cursor' clearly separates it from sibling lookups like get_ui_pattern, list_ui_patterns and search_ui_patterns that surface pattern data rather than build instructions.

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?

Gives clear context of use — generating prompts to paste into an external AI coding tool — and implies the natural inputs (ids, names or short descriptions). It does not state when NOT to use it or explicitly route to alternatives such as get_ui_pattern for plain pattern details, so it stops short of full when/when-not guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds a genuine behavioral trait beyond that: platforms with no native equivalent 'say so instead of naming one,' which tells the agent how to interpret a missing name.

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 and platform coverage are front-loaded in the first sentence, followed by two short clarifying sentences about the reverse lookup and the fallback. The long platform enumeration is dense but carries real information; no sentence is wasted.

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?

With no output schema, the description takes on the burden of describing returns, and it does: component names per platform, pattern equivalents, and the explicit 'no native component' fallback. What is missing is guidance on how it relates to the sibling pattern/compare tools.

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 100%, so both parameters are already documented in the schema, giving a baseline of 3. The description restates that query can be a pattern id/name/description or a framework component name and that platform is an optional single-platform filter, adding little beyond the schema's own examples.

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 pins down a specific verb (returns/works backwards) and a concrete resource (component names per platform), and it enumerates the platforms covered, so an agent can tell this is a cross-platform naming lookup rather than a pattern browser. It never names a sibling tool (e.g. get_ui_pattern, compare_ui_patterns), so differentiation is inferred rather than stated.

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 dual direction of the query (pattern → names, or component name → pattern) implies two usage modes, and the optional platform filter is mentioned, but there is no explicit when-to-use/when-not and no routing to siblings like get_ui_pattern or compare_ui_patterns. Usage must be inferred from the query semantics.

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

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior. The description adds genuine value beyond that by spelling out the payload contents (bilingual definitions, pronunciation, aliases, component names per platform, prompt, Q&A, related patterns, catalog URL), which tells the agent what it will actually receive.

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 core action, followed by a colon-list of return contents and a routing clause. Dense but every element is informative; the only minor cost is that the long field enumeration could be trimmed for a single-entry lookup.

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?

With no output schema, the description carries the burden of describing the return value and does so thoroughly, while also covering the single input and the id-discovery path. Nothing an agent needs to call and interpret this tool 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% for the single id parameter, and the schema already documents both the format and the sibling that lists all ids. The description's 'Takes an id' and the 'tabbar'/'bottomsheet' examples largely restate the schema, so it stays at the baseline.

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 (Returns) and resource (the full CatchUI entry for one UI pattern), scoped to retrieval by id. The enumeration of returned fields makes it immediately distinguishable from siblings like list_ui_patterns or search_ui_patterns, which return sets rather than full entries.

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?

Explicitly says it takes an id and routes the agent to search_ui_patterns to find ids from descriptions, with the schema adding list_ui_patterns as the id enumerator. Clear context for use, though there is no explicit when-not condition (e.g. preferring the narrower get_implementation_prompt or get_ui_component_names siblings when only one facet is needed).

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely useful context beyond that: the exact catalog size (61), the grouping by family, and the shape of each returned entry — meaningful for a tool with no output 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?

A single front-loaded sentence that leads with the action and scope, then packs the return fields, grouping, and filter into one clause. No filler or repetition despite the density.

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?

With no output schema, the description carries the burden of describing returns and does so well (ids, names, definitions, grouping). Minor omissions remain — ordering within a family and whether results are paginated or stable across calls — but these are low-impact for a 61-item static catalog.

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 100% and the single parameter is fully documented with an enum in the schema itself. The description restates the enum values and the optionality ('optionally filtered to one family') but adds no format or edge-case semantics beyond what the schema already provides, so the baseline of 3 applies.

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 precise verb and resource ('Lists the 61 UI patterns in CatchUI's curated catalog') and pins the scope as the full catalog rather than a query, which is what separates it from search_ui_patterns and get_ui_pattern. It also enumerates the returned fields (ids, English/Chinese names, one-line definitions), so an agent knows exactly what this call yields.

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 explains that the family filter is optional and enumerates the valid families, implying the usage pattern (call with no argument for the full catalog, with a family to narrow it). However, it never names an alternative or states when to prefer search_ui_patterns or get_ui_pattern over this, so the routing guidance is inferred rather than explicit.

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

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

Annotations already declare read-only, idempotent, closed-world, non-destructive behavior. The description adds useful behavioral context beyond that: it searches a curated catalog of 61 patterns and returns English/Chinese names, definitions, the best-matching Q&A, and catalog URLs, though it does not discuss no-result or ranking behavior.

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 definition is front-loaded with the core capability, followed by illustrative examples and a crisp usage sentence. It is appropriately sized with no wasted wording.

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 simple two-parameter search tool with full schema coverage and no output schema, the description is complete enough: it explains the search input style, the catalog scope, and the key return values an agent would need.

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 schema already documents both parameters, including limit. The description adds meaningful query semantics by showing that the query may be a plain-language description, question, term, and may be in English or Chinese.

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: finds the conventional name of a UI element or design pattern from a plain-language description, question, or term. It gives concrete examples and clearly scopes the catalog search, but it does not explicitly differentiate itself from siblings such as get_ui_pattern or list_ui_patterns.

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?

Explicitly says to use it when someone asks what a UI element is called or what a UI/UX term means. That gives clear positive usage context, though it does not mention when not to use it or which sibling to choose instead.

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