AIAgentCycle

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, covering the safety and side-effect profile. The description adds a useful note that facts_verified indicates whether key facts still appear on the About page, but says nothing about auth, rate limits, or caching. This is modest added context beyond annotations.

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 short sentences, front-loaded with the profile contents; the facts_verified note is efficient. The “lang is nl or en” clause slightly duplicates the schema but does not bloat the 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 simple one-parameter read tool with rich annotations and an output schema, the description gives enough to call correctly: what data is returned and the meaning of facts_verified. It lacks sibling-routing guidance, which prevents a 5.

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 only parameter is lang, with 100% schema coverage and its enum/default documented in the schema. The description's “lang is nl or en” duplicates the schema and adds no new syntax or semantic detail. Baseline 3 is appropriate when the schema fully documents the parameter.

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 the resource and enumerates the exact profile fields (summary, legal name, location, founder, focus and approach), so an agent knows it returns company identity data. It does not explicitly contrast with siblings like get_contact_info or get_faq, so it is clear but not fully differentiated.

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?

There is no explicit when-to-use or when-not-to-use guidance, no mention of alternatives, and no prerequisites. The content list implies company-info lookup, but it does not route the agent among sibling tools.

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?

The annotations already declare readOnlyHint, idempotentHint, and closed-world, so the safety profile is covered. The description adds a genuinely non-obvious behavioral boundary — that the server cannot send messages or book appointments — which prevents an agent from misreading a contact-info response as an actionable contact channel. It stops short of noting whether the details are static or dated, which keeps it off a 5.

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 short sentences, zero filler. The payload contents are front-loaded and the limitation follows, which is the right order for an agent scanning for whether to call it.

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-parameter read with full annotations and an output schema, the description covers what is returned and the key operational limit. The only omission is any note on freshness or availability of the contact channels, which is minor given the output schema carries the field-level detail.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. The description correctly spends no words on arguments and instead describes the returned payload.

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 the resource precisely and enumerates the four contact channels returned (email, phone/WhatsApp, contact page, assessment page), so an agent knows exactly what it gets. It doesn't explicitly contrast with siblings, but 'contact route' is a distinct resource from get_company_profile, get_faq, or get_service, making confusion unlikely.

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 implied rather than stated: an agent infers it should call this when a user asks how to reach the company. The second sentence provides a useful negative constraint (this server cannot send messages or book appointments), which heads off one class of misuse, but there is no explicit 'use this instead of X' routing and no mention of when contact info is not the right answer.

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 read-only, idempotent, non-destructive, closed-world behaviour, so the safety profile is covered. The description adds value beyond that by describing the payload (Markdown body plus source url, language, last-modified date), which tells the agent what it will receive and that language variants of a page exist.

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 sentences, zero filler: the returned content is front-loaded before the provenance hint. Every clause carries information the agent needs.

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 an output schema present, return values need not be fully spelled out, and the description correctly stays brief while still characterizing the payload and the id source. It omits failure behaviour for invalid or missing ids, which is the one remaining gap for a single-parameter lookup 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% and the single parameter already documents its origin with an example. The description only repeats the provenance of `id` (search_knowledge_base / list_documents) without adding format or edge-case semantics such as what an unknown id returns, so the baseline 3 is right.

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?

"Full text (Markdown) of one page" states a specific resource and scope (exactly one document) plus the return format. It never uses a verb like "fetch"/"read" and does not explicitly distinguish itself from look-alike siblings such as get_faq or get_service, so a small inference is still required.

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?

"Ids come from search_knowledge_base or list_documents" names the two alternatives and the workflow that selects them, which is genuinely actionable routing. It gives no explicit statement of when not to use this tool (e.g. for discovery or bulk retrieval), so it stops short of a full 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 read-only, idempotent, closed-world behavior, so the bar is lower. The description adds a genuinely useful trait beyond them: the content is verbatim from the pricing page, signaling it is a fixed snapshot rather than live or personalized data.

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 short sentences with the substantive purpose front-loaded. The trailing language note is mild redundancy against the schema but costs little.

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?

An output schema exists, so return values need not be described, and there is only one optional parameter. The description covers what the tool returns and its provenance, which is sufficient for a simple read-only lookup.

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 single lang enum already documents 'nl' and 'en' fully. The description's 'lang is nl or en' merely repeats the schema, so the baseline of 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?

The description states a specific resource and content scope: FAQs about prices, maintenance and approach, taken verbatim from the pricing page. That is clearly distinguishable from siblings like search_knowledge_base or get_service, though the distinction 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?

There is no explicit guidance on when to call this versus search_knowledge_base or list_services. The phrase 'verbatim from the pricing page' implies use for canonical, static answers, but the agent must infer the routing rule.

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, closed-world behavior, so the bar is lower. The description adds the important failure trait that an unknown id raises an error rather than returning empty, which is not derivable from the annotations.

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 short sentences, no waste, with the core identity of the tool front-loaded ahead of the id-provenance and error notes.

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?

An output schema exists, so return values need not be described, and the single parameter and safety profile are fully covered elsewhere. The error-on-missing behavior is the one piece of knowledge the description had to supply, and it does.

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 parameter description already explains the id format and examples. The description's note that ids come from list_services overlaps with what the schema states, so it adds little beyond the baseline.

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 (fetch one public service by id) and implicitly contrasts with list_services, which returns the collection. An agent can distinguish it from every sibling without opening the schema.

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?

Names list_services as the source of valid ids, which routes the agent correctly for discovery-then-retrieval flows. It doesn't explicitly say when not to use it (e.g. bulk reads), but for a single-record getter the context is clear.

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 non-open-world, so the safety profile is covered. The description adds only that results are published items with title/summary/url, which the output schema likely already covers; nothing about ordering, result limits, or missing translations.

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 short sentences, front-loaded with the resource and payload description. The closing lang sentence is largely redundant with the schema, a minor wasted line.

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 a single optional parameter, full annotation coverage and an output schema, the definition gives an agent everything needed to call it and to know the follow-up path via get_document. Only the missing sibling differentiation and result-size expectations keep it from a 5.

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 enum already documents nl/en including the default. The description's "lang is nl or en" merely restates the schema without adding fallback or selection semantics, so 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?

The description names a specific resource (published case studies, client and own projects) and states what each item carries (title, summary, url), so an agent knows exactly what comes back. It implicitly separates itself from get_document as the full-read path, though it doesn't differentiate from list_documents or search_knowledge_base.

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?

"Read one in full with get_document" gives an explicit routing rule to the sibling tool for the detail follow-up. It does not state exclusions (e.g., when to use search_knowledge_base instead for topical lookup), so it stops short of full when/when-not guidance.

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 the shape of each returned document, which is real context, but it says nothing about result volume, truncation or pagination – relevant for a whole-site catalogue – and an output schema already exists.

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 sentences, front-loaded with what the tool returns, followed by the filter options. Slightly dense phrasing ('Catalogue of the website') but no filler sentences.

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 only two optional parameters, an existing output schema and full safety annotations, the description is close to sufficient. Missing pieces are sibling routing and any indication of catalogue size/limits, which matter for an agent deciding between this and the type-specific list 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 description coverage is 100% and both parameters are enum-typed with defaults documented. The description's 'lang is nl or en' and 'type optionally narrows to: article, page, ...' merely restate the schema enums and add no new meaning.

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 makes clear this enumerates site documents and enumerates the returned fields (id, type, title, url, last-modified, summary), so an agent knows it is a full catalogue rather than a single-record fetch. It is weakened only by not stating that it spans all document types (article, page, integration, case, solution, sector) and therefore differs from the type-specific siblings list_cases/list_integrations/list_services.

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?

There is no explicit when-to-use or when-not guidance and no mention of alternatives such as list_cases, list_integrations, list_services, search_knowledge_base or get_document. The only implied usage is that the type filter narrows results, which a reader must infer.

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 non-open-world, so safety is covered. The description adds real behavioral context beyond that: it discloses the corpus size (200 systems, here 190), defines the three coverage statuses (productie = live in production, productie vs. standaard/mass-produced), and states the limits of the catalogue ('if it is not listed, it can probably still be integrated via one of four approaches'), which sets expectations about coverage gaps.

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?

Front-loaded with identity and corpus size, then value definitions, then filters — a sensible ordering. It is somewhat dense and restates enum glosses that also live in the schema, but there is no filler or marketing language.

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 an output schema present and 100% parameter coverage, the description need only supply scope and the meaning of the domain-specific status values, both of which it does. The one omission is what happens when no integration matches or whether results are paged/limited, which is not disclosed.

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 three of the five parameters are enums, so the schema already carries the semantics. The description's filter glosses (domain, status, query max 100 chars) largely duplicate the schema text rather than adding syntax rules, ordering behavior, or defaults not already stated.

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?

Opens with a specific verb+resource ('The integrations catalogue of aiagentcycle.com (190 systems)') and enumerates the fields returned, so the agent immediately knows this is a filterable list of third-party system integrations. It is clearly distinct from every sibling, which deals with contacts, services, cases, documents and knowledge-base content rather than integration systems.

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 enumerates the available filters (domain, status, category) and the meaning of each status value, which implies how to narrow a search, and adds the useful note that non-listed systems can usually still be integrated. However, it never states when to reach for this tool versus a sibling lookup or what happens when the name search returns nothing, so usage is implied rather than prescribed.

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, closed-world and non-destructive, so safety needs no restating. The description adds real domain context the annotations cannot: prices exclude VAT, are scoped to business clients, and carry a price_verified flag whose meaning (verbatim match on the live pricing page) is explained. It does not say how stale/unverified prices should be treated or whether results are cached, which would be the next useful layer.

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 tight sentences, zero filler. The core scope is front-loaded in sentence one and the caveat about price_verified follows as supporting 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?

An output schema exists, so return shape needs no prose, and annotations cover the safety profile. What remains — the commercial caveats around VAT, client type, and price verification — is exactly what the description supplies, leaving no material gap for a zero-parameter read 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. Schema coverage is 100% regardless.

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 resource (all public services and maintenance packages) and its payload (indicative prices), which contrasts cleanly with the singular sibling get_service. An agent can infer the list-vs-detail split without opening a schema, though the singular sibling is never named explicitly.

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?

"All public services" implies it is the discovery/listing entry point versus get_service for a single item, but there is no explicit when-to-use or when-not-to-use statement and no mention of alternatives. Usage is inferable from the sibling set rather than 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 safety is covered. The description adds real context beyond that: the OR-style matching and relevance ranking, the corpus breadth, the language constraint, and the id-to-get_document handoff. It does not discuss empty-result behavior or result counting, keeping it at 4.

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?

Front-loaded with the core purpose and corpus, then terse operational facts in short clauses. A few clauses (lang is nl or en, query max 100 chars, limit 1-10) duplicate the schema and could be cut without loss.

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 an output schema exists, the description need not explain return shapes; it instead supplies the parts the schema cannot: relevance ranking, corpus scope, query composition, and the follow-up call to get_document. Nothing required to invoke it correctly is missing.

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 baseline is 3; the description earns one more by disclosing that any word may match and that more matched words rank higher, which directly affects how the agent should compose 'query'. The lang/type/limit sentences largely restate enum values and bounds already in 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?

States a specific verb and resource ('Ranked full-text search over every page, solution, sector page, case, integration and article') plus the exact domain, aiagentcycle.com. This differentiates it cleanly from the enumeration siblings (list_documents, list_cases) and the fetch siblings (get_document) without needing to name 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?

Explains matching behavior ('Any word may match; documents matching more words rank higher'), which implies when this tool is appropriate versus listing. It also routes the agent forward by noting 'Each hit has an id for get_document'. No explicit when-not guidance or named alternative, so it stops 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.