Find an element type based on what you need it to do. Returns matches with four fields, and optional AI hints to guide your choice.
Find an element type by what you want it to do. Four fields per match; pass detail:true for the platform's AI hints, or read them with sb_traits_for once you have chosen.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Default 8 | |
| query | Yes | ||
| detail | No | Include useWhen / avoidWhen / contentTips per match |
Changes observed during successful MCP inspections.
v0.1.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that each match returns four fields and that detail:true adds platform AI hints, which is useful behavior beyond the readOnlyHint annotation. It does not explain what the four fields are, but it already goes beyond what the annotation alone provides.
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 no filler. The core purpose is front-loaded, and the detail:true versus sb_traits_for guidance is packed efficiently into the second sentence.
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 read-only annotation and simple schema, the description is mostly complete: it states what to search by, mentions the result shape, and routes follow-up actions. The absence of an output schema makes the 'four fields per match' note valuable, though the exact field names are left unspecified.
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 67%; detail and limit have schema descriptions, but query does not. The description adds meaning to detail ('platform's AI hints') and implies query semantics via the tool purpose, but it does not clarify limit behavior or query formatting, so it only partially compensates.
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 and resource: 'Find an element type by what you want it to do.' It clearly distinguishes the search use case from the sibling sb_traits_for, which is for reading trait details after choosing an element.
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 provides actionable guidance: pass detail:true for AI hints, or use sb_traits_for after selecting a match. This gives a clear context for using the tool and names a relevant alternative, though it does not enumerate exclusions for every sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.