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

Annotations already establish readOnly, idempotent, non-destructive and closed-world, so the safety profile needs no restating. The description adds genuinely new context: returns verbatim passages with source and link, includes 2026 tariffs, and serves Dutch or English pages depending on the query language.

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 bulk of the text is a long topic inventory that is effectively duplicated in the English half, so a large fraction of the description does not earn its place. The return-format information an agent actually needs (passages with source and link) is buried at the very end rather than front-loaded.

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 properly carries the return-value burden by stating that it returns passages with source and link and notes the 2026 tariff currency of the content. It is close to complete for a two-parameter search tool, with only search behavior (ranking, result count) left unstated.

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 description coverage is 100%, so both parameters are already documented in the schema; baseline 3 applies. The description adds one piece of behavioral meaning, that an English question yields English pages, which reinforces but does not extend the 'taal' enum documentation.

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 (searches) and resource (RadioMatic's knowledge base and branche pages), then enumerates the covered topics concretely enough that an agent knows this is the general Q&A retrieval tool. However, several listed topics (AI music, licentie costs, music advice) overlap with siblings like ai_muziek_voor_je_zaak and bereken_licentiekosten without any statement distinguishing this tool from them.

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 'Ook voor algemene vragen over achtergrondmuziek voor bedrijven' implies this is the catch-all for general questions, which hints at a division of labor with the calculators. But no sibling is named, no condition is stated explicitly, and there is no when-not guidance.

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