expand_mood_to_queries

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

Goes well beyond the lone destructiveHint=false annotation: it discloses the sampling path vs. static-map fallback, that no Spotify endpoint is called, that nothing is mutated, and the exact failure contract (isError after one retry, never a guess). This is rich, high-value behavioral disclosure.

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?

Four front-loaded sentences, each carrying distinct information (purpose, execution path, side-effect profile, error semantics). Slightly dense but no wasted text.

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 and a rich response_format parameter, the description carries the return-value burden and does describe the output fields. A brief note on which format actually gets returned on the static-map path would close the last gap.

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 mood, max_tokens and response_format are fully documented in the schema. The description adds the output vocabulary but no parameter-specific semantics beyond the schema, making the baseline 3 appropriate.

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 ('Turn a free-text listening mood into search terms') and enumerates the output shape (genres, keywords, terms to avoid). This is a unique utility with no equivalent among the siblings, so it is trivially distinguishable.

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 phrase 'for search' implies it is a pre-step to searching, but the description never states when to use this versus calling search/search_deep directly, nor any exclusions. Usage is implied rather than directed.

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