taste_recommendations

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

With no annotations provided, the description carries the full burden and delivers: 'read-only, no auth' declares the safety profile, 'Heuristic over stats.fm tops' reveals the data source and approximate nature, and the legacy-alias note explains the tool's status. It stops short of mentioning error behavior (e.g., unknown statsfm_user) but covers the critical traits.

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 compact sentences with zero waste: output shape first, then data source and safety, then routing note. The most decision-relevant fact (prefer the canonical name) is preserved in a trailing parenthetical that doesn't dilute the front-loaded core definition.

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?

Despite no output schema, the description names the output elements (evidence, risk note) so an agent knows what to expect. With 100% schema parameter coverage, auth/safety stated, and alias handling addressed, almost everything needed is present; the only gap is that 'bridge-mode' and 'listener's core' are defined only implicitly.

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%, so all three parameters are already documented and the baseline of 3 applies. The description adds only marginal param context (linking 'listener's core' to the user and 'stats.fm tops' to the data source) rather than new per-parameter meaning.

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+resource: 'Bridge-mode recommendations' of 'adjacent genres/artists between the listener's core and the unexplored', each with evidence and a risk note. It is immediately distinguishable from the many taste_* siblings by its precise scope and by explicitly flagging itself as a legacy alias of statsfm_taste_recommendations.

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?

Clearly routes the agent to the canonical sibling ('Legacy alias of statsfm_taste_recommendations — prefer the canonical name') and gives context for when it applies (bridge-mode exploration toward the unexplored). It does not contrast against other recommendation tools like taste_genre_bridge or exposure_check, so alternative-selection guidance is partial.

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