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

No annotations are present, so the description carries the full burden of behavior disclosure. It reveals a max 20 hit list, B-Ware note, no full-text descriptions, no full catalog enumeration, mandatory canonicalUrl display, and that images arrive as real content blocks that should always be shown. It does not mention auth or rate limits, but the key behavioral traits are well covered.

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?

The description is three sentences with the core purpose front-loaded, followed by precondition and behavioral output instructions. The third sentence bundles several relevant guidelines (canonicalUrl and image display) into one dense sentence, but it is still efficient and every clause adds operational value.

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, the description should explain return values enough for an agent to correctly render and act. It does state the hit list contains canonicalUrl and optional images, plus a B-Ware hint. Yet it doesn't disclose other likely result fields (title, composer, price, publisher) necessary for presenting a search result in most contexts, leaving a meaningful 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?

The schema already describes 100% of the parameters. The description adds search axes (title, composer, instrumentation, publisher) that map loosely to query, // 'composer', and 'instrumentation' properties, but it does not enrich parameter meaning beyond the schema and does not elaborate on `limit` or `bargainOnly` beyond what the schema states.

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 clearly states that the tool searches the sheet music catalog on musikalienhandel.de by title, composer, instrumentation, or publisher. It is a clear action+resource statement and naturally differentiates itself from siblings like search_instruments or search_bargain_stock, though it does not explicitly name any sibling.

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?

No guidance is given on when to use this tool compared to alternatives. Mentioning limitations like 'keine Volltext-Beschreibungen' and 'keine vollständige Katalog-Enumeration' partially implies when not to use it, but there is no explicit recommendation of when to pick check_bargain_alternative, get_product, or another sibling.

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