Skip to main content
Glama
Sign In

Bloom

by diy.bloom.api
OverviewDiscussionsAdmin

Search design inspiration

design_inspiration_search
Read-onlyIdempotent

Look at screenshots of real products before designing a frame. Describe in one query what the frame must show, and name a product or platform if one fits (e.g. 'issue list like Linear', 'mobile onboarding with a progress bar'). Returns the best-matching screenshots, best first. Use them for layout, hierarchy, density and type scale; never copy logos, brand assets or text. Returns { results: [{ imageUrl, mimeType, videoUrl?, preview? }] }, best first; the first screenshots are attached as images. Read-only; no project needed. Rate limited per caller.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "design_inspiration_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesWhat you want to see, in plain words: the screen's job and content, and any product or platform whose look fits. Example: 'weekly team calendar like Notion Calendar on web'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description adds real context beyond them: 'no project needed', 'rate limited per caller', results ordered best-first, and the first screenshots are auto-attached as images. That last point materially changes how an agent consumes the call and is not derivable from any structured field.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first sentence and the query-shaping guidance follows logically. Slight redundancy: 'Returns the best-matching screenshots, best first' is restated by the explicit return-shape sentence later, costing a few words without new information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

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 return-value burden and does so precisely, including field names, ordering, and side-channel image attachment. Rate limiting and the absence of a project dependency round out everything an agent needs to invoke and interpret the call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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 genuine search strategy the schema does not: describe the screen's job AND name a product/platform when one fits, with two worked query examples. Only minor value is added beyond the schema's own example.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('look at screenshots of real products') and frames it against a concrete moment ('before designing a frame'). No sibling tool does anything similar (browse_frame, code_search, read_frame_state are all inspection tools), so an agent can route here unambiguously.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear trigger ('before designing a frame') and even prescribes how to use the output ('layout, hierarchy, density and type scale; never copy logos, brand assets or text'). It stops short of naming an alternative or exclusion condition, but no plausible competing tool exists in the sibling list, so the gap is minor.

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

All Bloom toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources