iconify

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves data and returns specific fields (SVG body, width, height), which implies a read-only operation, but it does not disclose other behavioral traits such as error handling, rate limits, authentication needs, or whether it supports pagination for multiple icons. The description is minimal and misses key operational details.

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 a single, well-structured sentence that efficiently conveys the tool's purpose, scope, and return values without any redundant information. It is front-loaded with the core action and resource, making it easy to understand quickly, and every part of the sentence adds value.

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?

Given the tool's moderate complexity (2 required parameters, no output schema, and no annotations), the description is somewhat complete but has gaps. It covers what the tool does and returns, but lacks details on behavioral aspects like errors or limits. Without annotations or an output schema, the description should provide more context to fully guide usage, but it does the minimum viable job.

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 input schema has 100% description coverage, with clear documentation for both parameters (prefix and icons), including examples. The description does not add any additional meaning beyond what the schema provides, such as explaining parameter interactions or constraints. However, since schema coverage is high, the baseline score of 3 is appropriate, as the schema adequately handles parameter semantics.

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 specific action ('Retrieve'), resource ('SVG body data for one or more icons'), and scope ('in a specific collection'), distinguishing it from sibling tools like list_collections (which lists collections) and search_icons (which searches icons). It explicitly mentions what is returned ('SVG body, width, and height for each icon'), making the purpose unambiguous.

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 implies usage by specifying 'in a specific collection' and the return format, but it does not explicitly state when to use this tool versus alternatives like search_icons. It provides some context (e.g., retrieving data for icons in a collection) but lacks clear guidance on exclusions or direct comparisons to sibling tools, leaving usage somewhat inferred.

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 provided, the description carries full burden. It discloses the return format details (prefix, name, total icon count, author, license, category) which is valuable behavioral information. However, it doesn't mention potential limitations like pagination, rate limits, authentication requirements, or error conditions that would be important for a read operation.

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 a single, well-structured sentence that efficiently communicates both the action and the return format. Every element serves a purpose with zero waste - it states what the tool does and what information it provides without unnecessary verbiage.

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 read-only tool with no parameters and no output schema, the description provides adequate coverage of the purpose and return format. However, without annotations or output schema, it could benefit from more behavioral context (like whether this returns all collections at once or if there are limitations). The description is complete enough for basic understanding but leaves some operational questions unanswered.

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 (schema coverage 100%), so the baseline is 4. The description appropriately doesn't discuss parameters since none exist, focusing instead on the return values and purpose. This is the correct approach for a parameterless tool.

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 specific action ('List all available icon collections'), identifies the resource ('icon collections in Iconify'), and distinguishes from sibling tools (get_icons and search_icons focus on individual icons rather than collections). It provides a comprehensive verb+resource+scope statement.

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 implies usage context by specifying what information is returned (prefix, name, count, etc.), but doesn't explicitly state when to use this tool versus the sibling tools. No explicit alternatives or exclusions are mentioned, though the different resource focus (collections vs icons) provides some implicit 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?

With no annotations provided, the description carries full burden. It discloses the return format ('prefix:name' format) which is valuable behavioral context, but does not mention rate limits, authentication needs, pagination behavior, or error handling. The description adds some value but leaves significant behavioral aspects unspecified.

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 with zero waste: first sentence states purpose and scope, second sentence specifies return format with a concrete example. Perfectly front-loaded and appropriately sized for this tool's complexity.

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?

Given no annotations and no output schema, the description provides adequate purpose and return format but lacks details about error conditions, rate limits, authentication requirements, and result structure beyond naming format. For a search tool with 2 parameters, this is minimally complete but has clear gaps.

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 the schema already documents both parameters thoroughly. The description adds no additional parameter semantics beyond what the schema provides, such as search algorithm details or result ordering. Baseline 3 is appropriate when schema does the heavy lifting.

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 specific action ('Search for icons by keyword') and resource ('across all Iconify collections'), and distinguishes from sibling tools by focusing on keyword-based search rather than retrieval (get_icons) or collection listing (list_collections).

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 implicitly suggests usage for keyword-based icon searches, but does not explicitly state when to use this tool versus alternatives like get_icons or list_collections. It provides clear context about searching across collections but lacks explicit exclusions or named alternatives.

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