Minairal

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds value by enumerating the returned fact categories (useful since there is no output schema) but discloses nothing about behavior beyond content, such as freshness or response shape.

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 content is front-loaded with the subject (Verified facts about Minairal) followed by a dense content enumeration. It is a single long sentence with many comma-separated items, which is slightly unwieldy but every item earns its place as return-value documentation given no output schema.

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 effectively compensates by enumerating the full set of fact categories a caller can expect, which is the key completeness requirement here. The only gaps are language handling and explicit routing versus overlapping 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 description coverage is 100% and the single lang parameter is fully documented in the schema with its enum and default. The description never mentions language behavior, so it adds no meaning beyond the schema — 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 verb (get) and resource (company facts) and enumerates the exact categories returned — registration, team, stores, service centres, models, contacts. An agent can distinguish it as the broad company-facts source. However, it overlaps with siblings (contact/official links vs get_contact_options, stores with addresses vs list_locations) without acknowledging or differentiating 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?

There is no explicit when-to-use or when-not-to-use guidance, and no alternatives are named despite clear content overlap with get_contact_options and list_locations. The only usage signal is implicitly inferred from the content list, which leaves the agent to guess routing.

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 genuine value beyond them by enumerating what is returned (hours, response time, city-level trial availability) and clarifying that a prefilled WhatsApp message is not actually sent, which an agent needs to reassure users about.

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?

One front-loaded sentence whose colon-list enumerates the return payload, followed by a short read-only disclaimer. It is dense and slightly list-heavy but every clause earns its place; there is no filler or repetition.

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 carries the burden of describing results and it does so thoroughly (channels, hours, response time, trial availability). What is missing is only minor: it does not say what happens when the city is unknown or omitted, nor how the topic changes the returned form URL versus other channels.

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%, with enums and per-value explanations already in the schema, so the baseline is 3. The description implies city-scoped trial availability and topic-driven contact routing, but adds no format, default, or interaction detail beyond what the schema already provides.

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 pair: retrieving Minairal's contact channels (phone, WhatsApp, email, form, hours, response time, trial availability). Nothing overlaps ambiguously with get_company_facts, list_locations, recommend_system, or search_content, so an agent can route here for contact information without opening a 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?

The opening clause enumerates the user intents served (free trial, quote/site assessment, service, anything else), which maps directly to the topic enum and gives clear context for when to call. It stops short of naming exclusions or pointing to siblings for those adjacent cases, 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 readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds useful behavioral context beyond that: the fixed set of eight cities and the fact that store details only exist where a store is present, which sets expectations about partial results.

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?

A single front-loaded sentence that leads with the core subject (the eight technician cities) and then enumerates the returned fields. No filler or repetition.

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 wisely enumerates the returned fields (page URL, store address and hours, services, trial availability), which is what an agent needs to know. Only minor gaps remain, such as result ordering or the shape when no store exists.

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%, with city and lang both documented (including Thai script examples and the omit-to-list-all behavior), so the schema carries the load and baseline 3 applies. The description itself does not mention the language parameter or filtering syntax.

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 concrete verb+resource: the eight cities where Minairal technicians work, naming each city and the per-city data returned. An agent can distinguish this from get_company_facts, get_contact_options, or recommend_system 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?

The description implies the use case (looking up covered cities, store addresses/hours, services, trial availability), and the schema notes that omitting city lists all. However, it never states when to choose this tool over its siblings or any exclusions, leaving routing to inference.

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 the safe read-only, idempotent, closed-world profile, and the description goes further by disclosing the return contents (model facts, reasons, shop links, trial availability) and an explicit constraint (no prices, they live on product pages). With no output schema, this return disclosure is genuinely valuable.

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?

Four dense sentences, front-loaded with purpose then domain context then return/constraint notes. No filler sentences, though the Pure/Air explainer and the return list could be tightened slightly.

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 10-parameter, no-output-schema recommendation tool, the description covers purpose, the two required inputs, how to handle unknowns, and what comes back. It omits only minor points (e.g. that lang controls response language), which the schema already documents.

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% with rich enum descriptions, so the baseline is 3. The description does add useful domain framing ('Pure (shop name: Tap Water)', 'Air makes water from humidity'), which helps interpret pref/pipe, but the per-parameter detail is already fully carried by 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 ('Recommends two Minairal machines') plus the exact scope (best match + second option, or a Pure+Air pair) derived from a customer's situation. It is unmistakably distinct from the retrieval-oriented siblings (get_company_facts, list_locations, search_content).

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?

Gives clear context for use (matching the shop quiz 'Which one for me?' rules) and practical input guidance ('Only people and place are required; leave unknown answers out'). It does not name any alternative tool or a when-not-to-use condition, 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.

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description only needed to add context. It does: results are capped at 8 and include title, URL and snippet, which is genuinely useful operational detail about result volume and shape.

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 with zero filler; the scope is front-loaded and the result-shape sentence follows immediately. Every clause carries 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?

With no output schema, the description compensates by naming the returned fields and the 8-result cap, so an agent knows what to expect. It stops short of describing empty-result behavior or result ranking, a minor gap for a simple search 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 description coverage is 100%, with both the query and lang parameters documented in-schema including language options and examples. The description adds no parameter-level detail beyond the schema, 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 (keyword search) and resource (minairal.com content) and enumerates the corpora covered: system pages, guides, FAQ answers, sector/location pages, blog articles. This scope makes it readily separable from siblings like get_company_facts or list_locations without opening any 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?

The description implies the usage context (find site content by keyword) but never states when to prefer it over siblings such as get_company_facts or recommend_system, nor any exclusion. It is adequate but leaves routing to inference.

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