Skip to main content
Glama
Sign In

Blaze

by ai.blaze.app
OverviewDiscussionsAdmin

Search media library

search_media
Read-onlyIdempotent

Browse or search the photos and videos uploaded to a workspace's media library (these are not part of get_brand_kit). Returned URLs can be used in compose_design, set_design_background, replace_design_image, or as generate_image references.

Without query, lists the most recently used uploads, paged with page and limit (default 20, max 50); type selects "image" (default) or "video". With query, runs a semantic search over images only, and only over images Blaze has already indexed, so browsing is the complete list. Each result has a title, hosted URL, MIME type, dimensions, and media key. Read-only.

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": {
      "workspace_key": "<workspace_key>"
    },
    "name": "search_media"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoOptional 1-based page for browse mode. Defaults to 1.
typeNoBrowse "image" (default) or "video". Ignored when query is set (search is image-only).
limitNoOptional page size. Defaults to 20, capped at 50.
queryNoOptional. Semantic search over indexed images. Omit to browse recent uploads.
workspace_keyYesKey of the workspace to act in. Call list_workspaces to see the workspaces you have access to and their keys.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, and closed-world behavior, so safety is covered. The description adds non-obvious traits beyond them: default page size 20 capped at 50, semantic search coverage limited to Blaze-indexed images, and the fact that browsing is the complete list. It stops short of return-format details or rate limits, but the important behavioral caveats are disclosed.

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

Conciseness5/5

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

Front-loads purpose and sibling differentiation, then moves through mode behavior and result shape with no filler. Every sentence carries functional information, including the parenthetical exclusion of get_brand_kit and the downstream URL usage list.

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?

There is no output schema, but the description compensates by listing result fields (title, hosted URL, MIME type, dimensions, media key). Combined with the mode, pagination, and indexing caveats, an agent has everything needed to call this tool correctly for a read-only library search.

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. The description improves on that by explaining the interaction between query, type, and paging as a mode switch rather than isolated parameters, notably that type is irrelevant when query is set and that search is image-only. That relational context is meaningfully more than the per-parameter schema text provides.

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 pair (Browse or search) and resource (photos and videos in a workspace's media library), and immediately distinguishes itself from get_brand_kit. It also names downstream consumers (compose_design, set_design_background, replace_design_image, generate_image), so an agent knows both what it retrieves and how the output is used.

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

Usage Guidelines5/5

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

Explicitly explains the two operating modes and when each applies: omitting query lists most recently used uploads, while setting query runs semantic search. It also clarifies that search is image-only and limited to indexed images, so browsing is the complete list, which is exactly the kind of when/when-not distinction an agent needs before choosing a mode.

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

All Blaze 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