Digche Icons

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

No annotations, so the description carries the full burden; it does add real behavior context by noting that 'context' may be written in English or Persian and that results are ranked, plus that source can come from any library. It omits the return shape, the default candidate count, and whether ranking is deterministic — gaps a no-annotation mutation-free tool still needs covered.

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 the core action and scope, followed by a single actionable tip. No filler and nothing redundant with the schema.

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 five parameters, no annotations, and no output schema, the description does not say what a 'replacement' result contains (ranked names? library? preview?) or what the default limit is. It covers the essential calling intent but leaves an agent guessing about the response.

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 60%, so baseline is 3. The description does add semantic value for two parameters: enumerating valid sourceLibrary values and stating the context language flexibility. However, preferredStyle (9 enum values, default 'Linear') and the sourceLibrary parameter's relationship to sourceIcon are never explained beyond the 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 pair and resource ('find and rank ... replacements' for an icon) and names the supported source libraries (Lucide, Heroicons, Material Symbols, Font Awesome). It is clearly distinguishable from search_icons or list_categories by its replacement framing, though it never names a sibling explicitly to route the agent.

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?

Adds one genuine usage hint — supply UI context for a better match — but says nothing about when to prefer this over recommend_icons or search_icons, and no exclusions or prerequisites are given. The usage guidance is implied rather than stated.

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?

With no annotations, the description carries the burden and does disclose validation, defaults, and output-format contexts. However, it does not explain allowFallback behavior, what happens when a style or slug is unavailable, or other retrieval-side 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?

Three sentences, front-loaded with the core action and prerequisite, then style guidance, then format guidance. Every sentence adds distinct selection or usage information with no wasted prose.

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 four-parameter tool with no annotations, no output schema, and 0% schema description coverage, it covers the core retrieval and format choices. It is still incomplete because allowFallback semantics and fallback behavior are not described.

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%, so the description must compensate. It explains slug prerequisite, style preference/default, and format semantics well, but omits the allowFallback parameter entirely.

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 states a specific verb and resource: 'Retrieve a validated SVG variant' after selecting a Digche slug. It is clear what the tool returns, though it does not explicitly name sibling tools such as search_icons or preview_icons.

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?

It gives clear context for use: after selecting a slug, with 'Prefer Linear' unless another Digche style is already in use. The 'jsx' vs 'svg' guidance specifies when each format applies, but no explicit alternatives or when-not-to-use conditions are named.

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?

With no annotations, the description carries the burden of disclosing behavior. It adds meaningful context by stating it lists 'every published' category (scope) and includes 'icon count and available styles' (content). The phrase 'Call this once' also hints at low cost, which is helpful. It does not explicitly say it is read-only, but 'list' strongly implies that.

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 description is two sentences with no fluff. The first sentence delivers the core functionality, and the second sentence provides usage guidance. Every part earns its place, and it is front-loaded with the key action.

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?

The tool is simple (0 params, no output schema). The description covers what it returns (categories with counts and styles) and when to use it. It could explicitly state that it returns a list/array, but 'List every...' implicitly conveys that. It is complete enough for an agent to invoke correctly.

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?

The tool has zero parameters, so the description cannot add parameter-level meaning. The schema already covers everything (empty properties). The baseline for 0 parameters is 4, and the description appropriately does not invent unnecessary parameter details.

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 clearly states the tool lists every published Digche category, including icon count and available styles. It uses a specific verb ('List') and resource ('Digche category'), and it distinguishes itself from sibling tools like search_icons by focusing on catalog vocabulary rather than searching.

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 gives a clear 'when to use': 'Call this once to learn the catalog vocabulary before filtering searches by category.' It implies this is a one-time setup step and not for ongoing filtering, though it does not explicitly name alternatives or state when not to use it.

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?

No annotations are provided, so the description carries the full disclosure burden. It does reveal the key output behavior (a single composited image for human comparison, not machine-consumable data), but says nothing about payload size, latency, or what happens when supplied slugs are invalid or unmatched.

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, zero filler, with the purpose front-loaded and the two input modes following. Every clause carries information an agent needs.

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 annotations and no output schema, the description must do more of the work itself. It adequately explains the primary slugs/query flow but leaves the presentation parameters (style, theme, limit) and the failure modes of a purely visual tool undocumented.

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?

Adds real meaning beyond the schema for two of five parameters: slugs come 'from an earlier tool call' and query is a search-and-preview shortcut. The style, theme, and limit parameters are left entirely to the schema, and style/theme have enums but no descriptions, leaving the 60% coverage unresolved.

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 ('Render candidate Digche icons') plus the output form ('as a single image') and the reason ('so a person can compare them before choosing'). This meaningfully distinguishes it from get_icon_svg (a single SVG fetch) even though no sibling 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?

Gives two concrete invocation paths: pass slugs from an earlier tool call, or pass a query to 'search and preview in one step', which clarifies the relationship to search_icons. It stops short of stating when not to use this (e.g. when you only need markup, use get_icon_svg).

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?

No annotations exist, so the description must carry the behavioral load, and it does disclose real traits: a 20-slot batch cap, English/Persian input handling, and that the task string is used to disambiguate slot names. It omits what happens past the 20-slot limit and output size/performance implications, so not a 5.

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 short sentences, front-loaded with the core action and cap, then the disambiguation guidance, then the sibling comparison. No filler and nothing repeated from the schema.

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 and no annotations, the description covers the essential invocation context — batch limit, language handling, task's purpose. The remaining gap is output shape (plan vs assets payload size) which is only partly in the schema, but the core decision inputs are present.

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 80%, so the baseline is 3; the description adds a genuine layer by explaining WHY the task parameter matters (ambiguous slot names resolve correctly) and that slot names are language-agnostic. It says nothing extra about limitPerSlot, responseMode, or preferredStyle, which the schema already covers.

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 (pick/recommend), resource (Digche icon set), and scope (up to 20 named UI slots in one call), which cleanly distinguishes it from the per-icon siblings like search_icons. The 'coherent set' framing also signals it is a batched layout tool, not a lookup.

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 'Use this instead of one search per icon when laying out a screen,' naming the alternative pattern and the condition that selects this tool. It does not state when NOT to use it (e.g., single-icon lookups), which keeps it short of a 5.

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?

With no annotations, the description carries the full burden and does disclose useful behavior: bilingual English/Persian matching against stored Persian aliases, and a return of a paste-ready summary plus a preview image. It omits pagination/result-set behavior and any rate or scope limits, but as a read-only search those gaps are minor.

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 sentences, front-loaded with what is searched, then the Persian-language tip, then the when-to-use cue, then the return shape. No sentence restates structured data or could be cut without losing information.

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?

No output schema exists, and the description does step up by describing the return value. But for a 4-parameter tool with half its schema undocumented, leaving style and category entirely unexplained means an agent gets no guidance on when to narrow by style or category slug.

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 50%: query and limit are documented in the schema, while style (enum) and category (pattern) have no descriptions anywhere. The description reinforces that query is a functional intent rather than a literal name match, but adds nothing about style or category, so it does not compensate 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?

States a specific verb and resource (search published Digche icons) plus the searchable dimensions: name, alias, use case, tag, category, functional meaning. It does not name any sibling, so an agent must still infer how this differs from recommend_icons or preview_icons.

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?

"Use this before choosing a UI icon" gives a clear ordered context, and the Persian-wording tip is a concrete usage instruction. However, no alternative is named and no when-not condition is stated, even though recommend_icons and preview_icons look like overlapping siblings.

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