Clypmint B-Roll

Find b-roll

find_broll

Read-onlyIdempotent

Find verified b-roll for one subject: real photos and footage of exactly it, scored by a vision check, with license and source, best first. Use for any person, company, product, app, place, event or concrete scene a video mentions; for a whole script use plan_broll. Charged from the prepaid balance only when verified shots come back (broll_usage shows the prices).

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": "find_broll"
  }
}

Input Schema

Name	Required	Description	Default
`type`	No	Photos, footage, or either.	any
`limit`	No	How many shots to return at most.
`names`	No	Every named person, company, product, place or event in the request, as Wikipedia titles it, the most important first: ["Nelson Mandela"].
`query`	Yes	The subject to show: "Sam Altman", "Notion", "Shibuya Crossing", "barista pouring latte art".
`rights`	No	"licensed" (default): only media cleared for reuse. "any": also the open web, to get the real thing you name (a movie clip, a recent news photo, a screenshot of an event). Web results are marked license.cleared=false: the owner holds the rights, check before commercial use. Slower: about 7 s, at most 20 s.	licensed
`context`	No	The script line the shot plays over. Disambiguates and sharpens the pick.
`keywords`	No	Your own archive searches, 1 to 3 plain words each, nouns first, the most specific first: ["Mandela 1990", "Mandela crowd", "Nelson Mandela"]. Archives match every word, so "jazz band", not "vintage jazz band performing live". Send them and the search skips its own planning step (about 1 s faster).
`look_for`	No	What the right shot shows, with every detail that matters: "Nelson Mandela waving to a crowd after his release from prison in 1990".
`min_score`	No	Lowest vision score kept.
`orientation`	No	A preference: fitting shots come first.	any

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 29, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already cover read-only, idempotent, open-world and non-destructive, so the description's job is to add what they cannot: the billing rule ("charged from the prepaid balance only when verified shots come back"), which implicitly tells the agent empty results are free. It also discloses the license/source semantics of returned media, which is real behavioral context beyond the annotations.

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?

Three dense sentences with the core purpose front-loaded and the sibling routing in the second. Slightly run-on in the middle sentence, but no sentence is filler given the tool's breadth.

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

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter, open-world, billed search tool with no output schema, the description covers purpose, routing, cost timing and license meaning. It sketches the return shape (scored, licensed, sourced, best first) but doesn't say what an unsuccessful call looks like or how results are ordered beyond "best first".

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

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and every parameter already carries a detailed per-field description (including the rights enum's ~7s/20s latency note and the keywords planning shortcut). The description adds only the framing that the search targets exactly one subject; it does not add syntax or semantics the schema lacks, so the baseline 3 applies.

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 ("find verified b-roll for one subject") and immediately narrows scope: single subject, real photos/footage of exactly that subject, vision-scored, licensed, best first. It explicitly names the sibling it is not (plan_broll for a whole script), so an agent can route without opening either schema.

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?

Gives a positive usage condition (any person, company, product, app, place, event or concrete scene a video mentions) and a negative one ("for a whole script use plan_broll"). It also points to broll_usage as the alternative surface for pricing, covering the third sibling by name.

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

All Clypmint B-Roll tools Inspect

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.