statsfm_taste_recommendations

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

With no annotations provided, the description carries the full behavioral burden and does substantial work: it discloses read-only semantics, no-auth requirement, and that the output is heuristic (approximate, not guaranteed), plus the per-item output shape (evidence + risk note). This sets accurate expectations for safety and quality. It does not cover rate limits, determinism, or error behavior, but the essential operational traits are disclosed.

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 dense sentences deliver mode, scope, output structure, data source, heuristic nature, safety, and auth state in roughly 25 words. The key concept ('Bridge-mode recommendations') is front-loaded, and no sentence is redundant with the schema. This is efficient, telegraphic communication with zero waste.

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?

Given there is no output schema and no annotations, the description compensates well by naming the return shape (recommendations each with evidence and a risk note) and the operational profile (read-only, no auth). The remaining gap is disambiguation from the overlapping sibling `taste_recommendations` and any notes on how the three response_format values alter output — the schema documents the enum but not the practical differences between 'concise', 'detailed', and 'json'.

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 100% — all three parameters (statsfm_user, max_results, response_format) already carry descriptions in the schema, including defaults, constraints, and enum semantics. The description adds no parameter-level detail, so it correctly relies on the schema rather than duplicating it. Baseline 3 applies.

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 deliverable — bridge-mode recommendations — and defines scope precisely: adjacent genres/artists between the listener's core and unexplored territory, each with evidence and a risk note. It also identifies the data source (stats.fm tops) and heuristic nature. However, it never explicitly contrasts with the near-identically-named sibling `taste_recommendations`; the 'bridge-mode' qualifier implies the distinction without stating it.

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 context is implied through 'bridge-mode' (suggesting the user wants connections between known and unknown territory) and 'read-only, no auth' (suggesting safe, self-service use). But there is no explicit when-to-use guidance, no when-not-to-use conditions, and no routing to alternatives such as `taste_recommendations`, `taste_genre_bridge`, or `statsfm_exposure_check` — all of which exist in the sibling list and overlap in scope.

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