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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds genuinely non-obvious context that this endpoint requires Spotify app credentials while the rest of the platform is keyless, plus a 1-credit cost. It adds nothing about pagination, result caps, or empty-result behavior, which keeps it below a 5.

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 short sentences, front-loaded with the action and followed by the operational constraints, with no filler. The leading standalone "Search." is redundant with the sentence that follows and is the only wasted token.

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?

With no output schema, the description should tell the agent what a result looks like and how type/limit shape it, but it doesn't. It does cover the two things an agent can't infer elsewhere (auth requirement, credit cost), so it is adequate rather than complete.

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 description coverage is only 40% for 5 parameters, so the description must compensate: the phrase "tracks, albums, artists, podcasts or episodes" loosely maps to the type enum (with 'podcasts'/'episodes' corresponding to 'show'/'episode'), but limit, market, and cache_max_age receive no explanation anywhere. An agent must guess what limit does or whether market changes filtering.

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 ("Search Spotify's catalogue") and enumerates the searchable entity types, which separates it from the single-entity siblings like spotify_track or spotify_album. It stops short of explicitly saying 'use spotify_track when you already have an ID', leaving the boundary with siblings only implied.

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?

Usage is implied by "Search Spotify's catalogue" and the enumeration of types, and the credential note signals this is a different setup path from the keyless siblings. However there is no explicit when-to-use/when-not guidance, and the real alternative (fetch a known item directly via spotify_track/spotify_album instead of searching) is never mentioned.

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