Find references similar to a known reference by shared tags, categories, use cases, and StandOut direction ids. Use after finding one strong reference to broaden the evidence set.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of similar references to return, max 12 | |
| reference_id | Yes | Reference id from search_references | |
| response_format | No | Return markdown or structured JSON |
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 usefully explains the similarity criteria (tags, categories, use cases, direction ids), which is beyond the schema. However, it does not describe the output shape, result limits, or any side effects, leaving some behavioral ambiguity.
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, front-loaded with the core function, and every clause adds value. The usage guidance is integrated without redundancy.
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, the schema covers all parameters, and the description provides the key purpose and usage context. However, with no output schema and no annotations, a note about the return format would have made it fully complete.
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 schema has 100% description coverage for all three parameters, so the baseline is 3. The description adds no parameter-specific details, but the schema already fully documents reference_id, limit, and response_format.
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 uses a specific verb ('Find') and identifies a clear resource ('references similar to a known reference') with explicit matching criteria (shared tags, categories, use cases, StandOut direction ids). This distinguishes it from siblings like search_references or get_reference.
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 provides a clear contextual trigger: 'Use after finding one strong reference to broaden the evidence set.' This tells the agent when it is appropriate, though it does not explicitly name alternatives or 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.
Add one secure layer between your agents and this server.
Multiple tools have unclear boundaries: build_from_reference and build_from_reference_v2 serve nearly the same purpose, make_it_standout and polish_and_prove overlap heavily, and get_design_direction, synthesize_direction_from_references, and build_from_reference_v2 all produce design directions. The long descriptions help, but an agent could easily select the wrong tool.
Most tools follow a consistent snake_case verb_noun pattern (e.g., get_design_direction, search_references, watch_site). Minor deviations like client_report, make_it_standout, and polish_and_prove are acceptable but slightly break the pattern.
30 tools is too many for a design toolkit, exceeding the 25+ threshold for 'too many'. Many 'get' tools could be consolidated (e.g., get_hero_concept, get_motion_recipes, get_asset_pack could be one tool). The count feels bloated rather than well-scoped.
The tool set covers the full design/build/critique/report/watch lifecycle well, from direction and sections to client reports and site monitoring. Minor gaps exist (e.g., no explicit 'update' or 'delete' for references), but these are not critical to the core workflow.