RadioMatic: AI-achtergrondmuziek en muzieklicenties voor bedrijven

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safe/non-network read profile is fully covered. The description adds that the payload is a multi-part informational overview (providers, questions, further-reading links), but says nothing about return format or result size — acceptable given the annotation coverage.

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 resource is front-loaded, which is good, but the entire description is duplicated in Dutch and English, roughly doubling its length. The bilingual pairing is defensible given the taal toggle, yet the second block is pure repetition rather than additional 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?

For a read-only informational tool with no output schema, one fully-documented optional parameter, and annotations covering the safety profile, the description is nearly sufficient — it enumerates the content categories the agent will receive. The only missing piece is how this overview relates to the sibling comparison and advice tools.

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 100% and the single 'taal' parameter is fully documented with enum and default, so the schema carries the parameter burden. The bilingual phrasing of the description itself signals that content is language-dependent, which lightly corroborates the parameter but adds no syntax beyond the schema.

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 states a specific resource — providers of background music for businesses as listed by Buma/Stemra, plus the questions to ask each provider and pointers to further reading. It is clear what content is returned, but it never distinguishes itself from siblings such as vergelijk_opties, muziekadvies_voor_zaak or zoek_kennis, which all plausibly cover adjacent ground.

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?

'Voor wie een aanbieder van achtergrondmuziek of zakelijke muziek zoekt' identifies the audience, which implies when to reach for this tool, but there is no explicit when-not or named alternative. An agent must infer the boundary against the comparison and knowledge-search siblings.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the agent knows this is a safe, deterministic, closed-domain read. The description adds that the answer is an explanation of a fixed topic set, but discloses nothing further about return format, latency or freshness. With annotations carrying the safety profile, this is adequate but not rich.

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 main purpose is front-loaded in the first clause, and the Dutch/English duplication is defensible for a bilingual tool. However, the long keyword-stuffed tail ('AI-radio of instore radio met AI, muziek die met AI gemaakt is, achtergrondmuziek voor bedrijven...') repeats concepts already stated and adds bulk without new information.

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?

For a single-parameter, read-only content tool with annotations covering the safety profile and no output schema, the description fully scopes the subject matter an agent can expect. The main residual gap is routing: it never says how this topic page relates to zoek_kennis or the pricing/licence calculators, so an agent must infer the choice.

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?

There is one optional parameter (taal) with 100% schema description coverage and an enum with a default, so the schema already documents it fully. The description never explicitly explains the taal parameter, though the bilingual Dutch/English text implies language selection. Baseline 3 applies when the schema does the work.

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 names a concrete subject and enumerates what it covers: what AI background music is, how RadioMatic works, why no Buma/Stemra/Sena fees apply, pricing, and how it differs from radio or royalty-free music. It is clearly an informational/topic-explainer tool rather than an action tool. It does not, however, differentiate itself from siblings such as zoek_kennis, bereken_licentiekosten or pakketten_en_prijzen, even though its 'wat het kost' scope overlaps with 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?

Usage is only implied through a trigger-phrase list ('Voor vragen over AI-muziek in de winkel, AI-radio of instore radio met AI...'), which suggests when the topic matches. There is no explicit statement of when to prefer this over zoek_kennis or bereken_licentiekosten, and no exclusions are given.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), and the description adds substantial extra context: amounts are excluding VAT and before discounts, results are per location and for all locations combined, each amount cites its tariff-table source, and the calculation uses the official staffels rather than an estimate. It also discloses the graceful degradation to a from-price when optional inputs are missing.

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 first sentence front-loads the core purpose well, but the text is long and partially redundant: the Dutch use-case enumeration (winkel, kapsalon, praktijk, kantoor, horeca…) is largely repeated in the English paragraph, and the save-with-licence-free-music angle is a second tool's job. Trimming the repetition would sharpen it considerably.

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 and nine parameters, the description carries the return-value burden and does reasonably well: it states currency basis (excl. btw), granularity (per vestiging and total) and sourcing per tariff table. It does not describe the result object's shape or rounding, which is the only notable gap for a calculation tool.

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 100%, so the schema already documents all nine parameters and the baseline is 3. The description adds genuine semantics beyond the schema: what happens with missing oppervlakte/fte (from-price), the per-location vs total split, and that the saving calculation includes the current subscription — useful behavioural meaning not encoded in the fields.

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 gives a specific verb+resource: calculating annual base tariffs of Buma/Stemra and Sena for background music, with 2026 rates and per/all-location breakdown. It is highly distinguishable from most siblings by subject matter, but it never names or contrasts with neighbours such as check_licentieplicht, pakketten_en_prijzen or vergelijk_opties, so a 5 is not warranted.

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?

Usage context is clear: it is for shops, salons, offices, hospitality, hotels, gyms, pools, saunas and spas, and explicitly says it still returns a from-price when surface area or employee count is unknown. However, it gives no exclusions and does not route the agent to an alternative tool, so it stays below the 'explicit when/when-not/alternatives' bar.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description's own contribution is the note that the answer comes with 'uitleg, bronnen en wat je kunt doen', which usefully signals output content in the absence of an output schema. It adds nothing about decision logic, caveats or how authoritative the advice is.

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?

Purpose is front-loaded in the first clause, but the middle section enumerates use cases that largely duplicate the enum values in the schema, and the full English translation repeats everything already said in Dutch. Roughly a third of the text is redundant for an agent that reads both schema and description.

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?

For a read-only, closed-world advice tool with fully documented parameters and no output schema, the definition covers what it does, when to reach for it, and what kind of answer comes back. Only the boundary against sibling tools (cost calculation, package comparison) is left for the agent to infer.

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% and both enums carry detailed per-value explanations, so the schema does the heavy lifting. The description only restates the axis ('afhankelijk van de geluidsbron en wie de muziek hoort') and adds no interpretation beyond it, which is the baseline case.

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 states a specific verb and resource: it determines whether a Dutch business needs a Buma/Stemra and/or Sena licence based on the sound source and audience. Scope is further narrowed to the Netherlands and to specific sources (radio, TV, Spotify, business streaming). It does not, however, distinguish itself from close siblings such as bereken_licentiekosten (cost calculation) or muziekadvies_voor_zaak, so the boundary is implied rather than stated.

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?

Multiple concrete trigger scenarios are spelled out: after receiving a letter or invoice from Mijnlicentie, when radio/Spotify/TV is on in the business, when only staff hear the music, and when the user wants to know whether music may be played and how to arrange it. That is rich when-to-use context. There are no explicit exclusions or named alternatives, so it falls short of a 5.

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

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real content: it discloses the scope (38 business types), the granularity (per zone and day of week), and that it explains existing-equipment operation. These are useful behavioral traits beyond the structured fields.

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?

Content is front-loaded and each clause describes a distinct facet (music fit, equipment, RadioMatic role). The Dutch and English versions are essentially duplicative, which lengthens it, but the purpose sentence leads and nothing is buried.

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?

For a read-only, 2-parameter tool with no output schema and full schema coverage, the description supplies enough scope (business types, zone/daypart, equipment) for an agent to call it correctly. Only the routing-vs-siblings gap remains open.

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% and both parameters (taal, soort_zaak) are documented with enums, so the schema carries the load. The description reinforces the soort_zaak domain (38 types) and the bilingual taal behavior, but adds no syntax or format detail beyond the schema.

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?

Specific verb+resource: it advises which music/background music suits a type of business, per zone and time of day, plus equipment compatibility. The 38-business-type scope is concrete. It doesn't explicitly name which sibling it is vs (ai_muziek_voor_je_zaak, zoek_kennis), so it stops short of full differentiation.

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?

'Ook voor wie zoekt welke achtergrondmuziek, playlist of sfeer bij zijn zaak past' implies the use case of finding suitable music for a business. But there is no explicit when-to-use/when-not, no prerequisites, and no routing against the similar-sounding siblings like ai_muziek_voor_je_zaak or zoek_kennis. Usage is only implied.

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

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

Annotations already declare readOnlyHint/ idempotentHint and openWorldHint=false, so safety is covered. The description adds useful content-level context (what the response covers: plans, inclusions, terms, the 10-location Enterprise threshold), but much of it is marketing copy rather than behavioral disclosure, and it says nothing about data freshness or how the answer is scoped.

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 purpose is front-loaded in the first clause, but the entire text is duplicated in Dutch and English, roughly doubling length with zero added information. The second half of the Dutch sentence is a dense run-on of pricing and product claims.

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?

For a zero-required-parameter read-only lookup with no output schema, the description gives enough of the response shape (plans, per-location prices, inclusions, terms) to set expectations. It misses only routing guidance against the pricing/advice siblings.

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 100%, so the single parameter is already documented. The description never names aantal_vestigingen, though 'prijzen per locatie' and 'Vanaf 10 vestigingen: Enterprise' implicitly hint that location count drives the tier, which is a marginal gain over the schema.

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?

Concrete verb+resource: it returns RadioMatic's plans with per-location prices, plan contents, and terms. An agent can tell this is a static plan/price catalog rather than a cost calculator or comparison tool, though the description never names the siblings it differs from (bereken_licentiekosten, vergelijk_opties).

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?

Usage is only implied: an agent infers it should call this for an overview of plans and pricing. There is no explicit when-to-use, no exclusion of the cost-calculation or comparison siblings, and no prerequisites stated.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real context beyond that — the link is pre-filled from the conversation and it alludes to 'wat er daarna gebeurt' — but never says what actually happens after the trial, so the disclosure stays partial.

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?

Two front-loaded sentences that get to the point immediately, with the core action first and the pre-fill behaviour second. The English restatement is near-verbatim duplication, which pads length without adding information, but it is a minor cost.

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?

A read-only, idempotent link-generation tool with full schema coverage and no output schema — the description need not explain return values. Combined with the annotations it is complete enough to invoke correctly; only the vague 'what happens next' reference leaves a small 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?

Schema description coverage is 100%, so every parameter (fte, platform, soort_zaak, oppervlakte_m2, aantal_vestigingen) is already documented, including the enum mapping rules. The description only adds that these values are drawn from the conversation, which the schema descriptions already state, so the baseline 3 applies.

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 and resource: it hands back a link for a 14-day free trial of RadioMatic, and notes the link comes pre-filled from the conversation. This is distinguishable from siblings like bereken_licentiekosten or pakketten_en_prijzen, though no sibling is named to make the boundary 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?

Usage is only implied: the mention of 'de situatie uit het gesprek' signals it belongs inside a live customer conversation where details are already known. There is no explicit when-to-use, when-not, or pointer to alternative tools such as vergelijk_opties or aanbieders_overzicht.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered and the description only needs to add substance. It does add what gets included in the comparison (licence fees where applicable), which is useful. With no output schema present, however, the description never says what the result looks like (a ranked cost table? per-option breakdown?), leaving a real gap for a computation tool.

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 lead sentence is well front-loaded and dense with useful scope information. The remainder restates the same audience targeting once in Dutch and again in English, so a sizeable share of the text is verbatim duplication that does not add decision-relevant detail.

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?

Seven parameters, one required, no output schema, and a branch enum with 47 values — a moderately complex pricing model. The description explains the scope of the comparison but not the shape of the answer or how inputs such as fte, oppervlakte_m2 and aantal_vestigingen drive the costs, which is what an agent would need to report results credibly.

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% and the enum for soort_zaak even documents edge-case mappings, so the schema does the heavy lifting and a baseline of 3 applies. The description adds only indirect meaning by stating that licence fees are factored in, implying why surface area, waiting room size and headcount matter, but it does not explain how any parameter affects the comparison.

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 first sentence names a concrete operation (putting yearly costs side by side) and enumerates the exact options compared: radio, business streaming services, royalty-free, RadioMatic, plus Buma/Stemra and Sena fees. That is a specific verb+resource combination an agent can act on. It stops short of naming the closely related siblings (bereken_licentiekosten, aanbieders_overzicht), so the boundary between 'compare total costs' and 'calculate licence fees' must be inferred.

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?

It gives clear intent-based triggers: for anyone wanting the best and cheapest way to arrange in-store music, or seeking a cheaper alternative to their current service. That covers the typical use case well. It offers no explicit exclusions or pointer to the sibling that should be used instead when the user only wants licence costs or a provider list.

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

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.