search_advanced

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: fields are 'quoted and composed for you,' the quota is explicitly stated ('🟢 one GET /search call'), and tag semantics are clarified. However, it doesn't disclose return format, error behavior for invalid field combinations, or pagination behavior with max_results — though the response_format parameter partially covers output via the schema. Decent but not rich 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 sentences with the core purpose front-loaded before the syntax reference. The filter syntax list is dense but earns its place since it enumerates the tool's core capability. The quota note is compact and useful. Slightly long, but every sentence contributes — no filler or tautology.

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 description fully covers the mechanics (what filters, composition behavior, cost), which is the hard part given the nested fields object. But with zero annotations and no output schema, the missing pieces matter: no sibling routing among ~15 search tools, no note on how this differs from search_deep/search_fresh, and no hint about return behavior beyond the schema's response_format. Adequate for calling the tool, incomplete for confidently choosing it.

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 83%, so the high-coverage baseline of 3 applies. The description genuinely adds value beyond the schema: it explains tag:new means 'last ~2 weeks' and tag:hipster means 'lowest-popularity' (the schema only lists the enum values), shows the year range syntax (year:1984 / year:1980-1989) with example formats for isrc/upc, and clarifies that fields are auto-quoted. That is real semantic enrichment, not schema repetition.

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 ('builds a valid Spotify filter query from typed fields and runs it'), which clearly distinguishes it from simple keyword search siblings. The 'structured advanced-search composer' framing signals this is the field-based search tool. However, it doesn't name which sibling it competes with, and with 15+ search variants (search_tracks, search_deep, search_fresh, search_by_isrc) the differentiation is implied rather than explicit.

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?

'Pass whichever fields you have' gives clear input guidance, and the syntax list tells the agent what filter fields are available. But there is no explicit when-to-use vs alternatives — no statement like 'use search_tracks for simple keyword queries' or 'use search_by_isrc for ISRC-only lookups.' With a crowded sibling family, explicit routing would materially help an agent avoid picking the wrong search tool.

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