Skip to main content
Glama

ProofProfile evidence (paid proof, free name search)

find_recording

Read-onlyIdempotent

FREE. Discover recordings by artist name, or read one artist's sealed catalogue by artist_id. Supply exactly one of artist or artist_id, optionally title and page. Name search is partial: at most three artist files are read; artistCandidates lists the returned name matches, not necessarily every namesake or only census artists. Show returned recording matches with a brief incomplete-search warning; avoid attributing all matches to one artist without evidence or asking people to pick between indistinguishable IDs. If an artist ID was supplied, use it directly and confirm the selected name and ID. Select an artist_id from those candidates and page through that artist's matching recordings, 25 per page. Release pages are listing context, not proof of a release. Verify the intended recording by ISRC. A name-search miss does not establish absence.

Input Schema

NameRequiredDescriptionDefault
pageNoPage of matching recordings, 25 per page, with or without title
titleNoRecording title, for example The Boys of Summer. Leave it out for all of the artist's recordings.
artistNoArtist name, for example Don Henley
artist_idNoRegistry artist id from artistCandidates or an artist page; use instead of artist

Output Schema

NameRequiredDescriptionDefault
pageNo
@typeYes
genreNo
queryYes
scopeNo
answerYes
statusYes
artistsYes
@contextYes
coverageNo
numberOfItemsNo
numberOfPagesNo
similarArtistsNo
itemListElementNo
artistCandidatesNo

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 cover the safety profile (readOnly, idempotent, closed-world), and the description adds substantive behavior beyond them: the tool is free, name search reads at most three artist files, artistCandidates are partial name matches rather than every namesake, results come 25 per page, and release pages are listing context rather than release proof. It also discloses how to present incomplete results, which is real caveat-level context.

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?

Front-loaded with the cost signal ('FREE.') and the core capability, then layered with cautions. A few clauses are dense and slightly convoluted ('not necessarily every namesake or only census artists'), but nearly every sentence carries operational content.

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?

Covers the full workflow an agent needs for a four-parameter, partially-matching search tool: input exclusivity, candidate selection, pagination, result presentation caveats, and downstream verification. With an output schema present, no return-value detail is missing.

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 meaning the schema does not: the exactly-one-of rule with its consequences, the partial nature of artist matching, and how page interacts with title filtering. It stops short of describing output-field shapes, which the output schema presumably covers.

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 ('Discover recordings') plus two distinct modes: name search and reading one artist's catalogue by artist_id. An agent can immediately tell this is a discovery/lookup tool rather than a verifier.

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 explicit usage rules: supply exactly one of artist or artist_id, use artist_id directly when supplied, and page through candidates when only a name was given. It also warns that a name-search miss does not establish absence and points at ISRC verification, though it never names verify_recording as the alternative to switch to.

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