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

With no annotations, the description carries the full burden and does real work: it discloses the data sources (Discogs-derived identifier index plus MusicBrainz fallback), the known coverage gap for music-club numbers, and the risk of false-positive matches requiring manual verification. It does not say what a miss looks like or whether matching is fuzzy vs exact, which is the remaining behavioral unknown.

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

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

Three dense sentences, each doing distinct work: purpose plus accepted formats, then the coverage caveat with verification advice, then return shape and provenance. Front-loaded and waste-free; the trailing human-tool URL is the only element that does not serve an agent caller.

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

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

No annotations and no output schema, yet the description covers all three things an agent needs: what to pass in, what comes back (artist, album, year, label), and how much to trust a result. The known-unreliable input class is called out, which is exactly the failure mode that would otherwise cause silent wrong answers.

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

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 earns above that by explaining what kinds of values the single `identifier` param accepts (DIDX IDs, label catalog numbers, barcodes) with format examples, and by flagging one input class as unreliable — meaning an agent can pre-filter calls rather than just passing a raw string.

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

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

States a specific verb and resource ("Identify a CD from a number printed on it") and enumerates the identifier families accepted (DIDX hub/master IDs, label catalog numbers, barcodes) with concrete format examples. The CD framing plus the stated return fields (artist, album, year, label) make it distinguishable from sibling lookups like nmlp_vinyl_lookup and nmlp_lccn_lookup without opening any schema.

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

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

Gives a clear use condition (a number printed on the disc hub, spine, or barcode) and an explicit when-not: music-club "D ######" numbers are not reliably covered and a hit can be a different album, so verify artist/title against the disc. What it lacks is routing to an alternative tool for those unsupported cases — with 16 siblings, naming the fallback (e.g., vinyl lookup or search_titles) would close the gap.

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