Skip to main content
Glama

Look the artist up online

find_online
Destructive

Runs Audora's own lookup of what the artist has already published (streaming profiles, releases, their site and social profiles), or reads where one is and what it found. Use it only when you cannot search the web yourself: otherwise look the artist up with your own search, check with them that you found the right artist, and fill their page with update_profile. With action "start" it begins one, which takes 1–2 minutes; the artist gets a few a day, shared with Soundcheck in Audora. The account's first lookup is free and each later one costs credits and needs the artist's spend permission: start with dry_run: true to read the price, tell the artist, then start with confirm_cost_credits. With action "status" (the default) it reads the newest lookup, or the one named by run_id. Every fact comes with the pages it was read on. It never changes the artist's profile: when it is done, call propose_profile so the artist keeps what is theirs in Audora.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_online"
  }
}

Input Schema

NameRequiredDescriptionDefault
linkNoFor start: one page the artist is on (Apple Music, Deezer, SoundCloud, YouTube, Bandcamp, their site, Instagram), as a full https:// address. It is the best starting point. A Spotify link is kept as theirs but never opened, so another page starts the lookup better.
actionNo"start" a new lookup, or read its "status". Default: status.
artistNoOnly when you are connected as a label: the roster artist this call is for — their artist_user_id from list_roster, or their exact artist name. Required for every artist tool on a label connection. Leave it out on an artist's own connection.
not_meNoFor start: names of earlier matches the artist said are not them.
run_idNoFor status: a particular lookup. Default: the newest.
dry_runNoFor start: true to read what the lookup costs without starting it.
confirm_cost_creditsNoFor start: the price a dry run quoted and you told the artist. Needed for a lookup that is not free.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / confirm_cost_credits
      Added value: +{
      +  "description": "For start: the price a dry run quoted and you told the artist. Needed for a lookup that is not free.",
      +  "type": "number"
      +}
    • addedInput schema / properties / dry_run
      Added value: +{
      +  "description": "For start: true to read what the lookup costs without starting it.",
      +  "type": "boolean"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / link / description
      Previous value: -"For start: one page the artist is on (Spotify, Apple Music, Deezer, SoundCloud, YouTube, Bandcamp, their site, Instagram), as a full https:// address. It is the best starting point."New value: +"For start: one page the artist is on (Apple Music, Deezer, SoundCloud, YouTube, Bandcamp, their site, Instagram), as a full https:// address. It is the best starting point. A Spotify link is kept as theirs but never opened, so another page starts the lookup better."
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations it discloses duration (1–2 minutes), a rate limit shared with another Audora feature ("a few a day, shared with Soundcheck"), and a full cost/authorization model (first lookup free, later ones cost credits and need the artist's spend permission, dry_run → confirm_cost_credits). It also scopes the side effects precisely — it never changes the artist's profile and the follow-up is propose_profile — which is exactly the context needed alongside destructiveHint=true and openWorldHint=true.

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?

The routing decision (use your own search unless you can't) is front-loaded and every sentence carries real information. It is dense — the cost and permission chain plus the propose_profile handoff make it long — but nothing is genuinely redundant; the only repetition is restating that status is the default action.

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?

For a costly, slow, asynchronous, open-world tool with no output schema, the description covers duration, rate limits, billing, required confirmation, return provenance ("every fact comes with the pages it was read on"), and what must happen afterwards. An agent has everything needed to call it safely and interpret the result.

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 workflow meaning the schema does not: dry_run must be followed by telling the artist the price and then supplying confirm_cost_credits, and status defaults to the newest run unless run_id is given. It stops short of explaining `not_me` or `link` selection in the prose, leaving those to the schema descriptions.

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?

"Runs Audora's own lookup of what the artist has already published (streaming profiles, releases, their site and social profiles), or reads where one is and what it found" names a specific verb (lookup/read) and a concrete resource (the artist's published presence), and explicitly separates the two modes via action. It is clearly distinguishable from the sibling mutation tools update_profile and propose_profile, which it names.

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?

It gives an explicit exclusion ("Use it only when you cannot search the web yourself") plus the full alternative path: run your own search, confirm with the artist, then fill the page with update_profile. It also states the mode-selection rule ("status" is default, "start" begins a run) so the agent knows which action to pick.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources