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

Annotations already mark the tool as read-only and idempotent, covering its safety profile. The description adds valuable behavioral detail: it searches both a knowledge bank and branch pages, and it returns passages with source and link. This goes beyond the annotations by clarifying the nature of the output and the data sources consulted, giving the agent a clearer expectation of the result format.

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 a single paragraph that front-loads the core action ('Zoekt in de kennisbank en de branchepagina's...') and then expands with a list of relevant topics. It is not overly verbose, and each listed topic helps define the tool's scope. The final sentence about returning passages with source and link is concise and useful. While it could be trimmed slightly, it remains appropriately structured for the information it conveys.

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 that this is a straightforward search tool with only two simple parameters and no output schema, the description provides sufficient context: it identifies what is searched, lists the covered domains, and indicates the return type (passages with source and link). It does not need to elaborate on pagination or result counts, as the annotations already establish safety and idempotency. The information is complete for an agent to invoke the tool correctly.

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 covers both parameters (vraag and taal) with descriptions, achieving 100% schema coverage. The tool description does not add any additional meaning about these parameters; it only restates the general context of searching. According to the calibration, a baseline of 3 is appropriate when the schema already explains the parameters, and the description provides no extra nuance.

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: searching RadioMatic's knowledge base and branch pages for answers to business-music questions. It specifies the resource (kennisbank and branchepagina's), the action (zoekt), and the scope (Dutch business music licensing topics). The extensive list of covered subjects (Buma/Stemra, Sena, Mijnlicentie, streaming, etc.) makes it unambiguous and distinct from siblings that perform specific calculations or checks.

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 clear context for when to use this tool by enumerating the exact topics it addresses (e.g., licenses, invoices, equipment, music genres per space). While it does not explicitly mention alternatives or when not to use it, the broad topic coverage implies it is the general-purpose search tool, whereas siblings like check_licentieplicht or bereken_licentiekosten are narrowly focused. No exclusions are given, but the context is sufficient for an agent to select it for factual queries.

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