era_preference_report

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

With no annotations, the description carries the full burden and does meaningful work: it discloses the exact quota (recently-played + 1× top-tracks), the default window (medium_term), and the comparison methodology. The two GET endpoints strongly imply a read-only operation. It stops short of stating non-mutation explicitly or covering rate-limit and edge behaviors, but the operational disclosure is substantial.

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?

Two sentences, zero filler: the purpose statement is front-loaded and the quota line packs operational value that would otherwise be missing entirely. Every word earns its place.

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?

The definition covers what the tool does, its data sources, the default window, and cost, while the response_format enum partially describes output shapes. With no output schema, the report's actual return structure is left unspecified and edge cases (e.g., insufficient listening history) are unaddressed — minor gaps for a moderate-complexity read-only analytics tool.

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% with solid per-parameter descriptions and enums for two parameters, so the baseline is 3. The description's only parameter reference, 'default medium_term', duplicates the schema default and adds no new meaning for max_items or response_format.

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?

The description names a specific verb ('compare'), a precise resource ('decade mix of recently-played tracks' vs 'top-tracks window'), and the insight it produces ('skews older or newer'). Naming both data sources distinguishes it from raw retrieval siblings (get_recently_played, get_top_tracks) and adjacent era tools (era_distribution_report, playlist_era_profile) without needing to open the 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?

The intended context is implied — use when you want recent-listening era skew measured against a top-tracks baseline — but no alternatives are named and no when-not-to-use conditions are given. Siblings like era_distribution_report and playlist_era_profile occupy adjacent territory, so an agent gets no explicit routing guidance.

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