Passende Skills finden

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

Beyond the readOnly/idempotent annotations, the description reveals important behavioral traits: the search is lexical (not semantic), the catalog is scanned across specific fields (name, aliases, tags, category, description), and scores are only comparable within a single query. This adds significant context about the tool's internal workings and limitations.

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 efficiently structured in three sentences: purpose, critical usage warning, and supplementary details about scoring. Every sentence adds value, and the most important instruction (use keywords) is highlighted with 'WICHTIG' to draw attention. No redundant wording.

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 the tool's moderate complexity (5 parameters, no output schema), the description adequately covers purpose, input query format, matching logic, and a caveat about score comparability. It briefly indicates the return includes best candidates with matched terms, but lacks detail on result structure (e.g., fields like score, name). This is a minor gap, not a critical omission.

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 input schema already provides 100% parameter descriptions, including the intent parameter's keyword guidance. The description reinforces the lexical matching behavior but does not add new semantic details about individual parameters beyond what the schema already specifies. Therefore, baseline 3 is 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?

The description clearly states the tool's purpose: recognizing which skills match a task or intent. It distinguishes itself from sibling tools like list_skills by emphasizing that it evaluates and ranks skill candidates based on lexical matching over name, aliases, tags, category, and description, rather than simply listing all skills.

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 description provides concrete usage guidance: query with keywords/technical terms, not whole sentences, because the search is purely lexical and full sentences attract false hits. It gives context on how to formulate the intent parameter and warns about score comparability across queries, though it does not explicitly name alternative tools or state when not to use this tool.

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