GCC Domestic

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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds useful content scope (the canonical link categories returned), but says nothing about return structure, staleness of links, or whether the country filter changes the payload.

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: the first defines the resource and its contents, the second gives usage. Nothing is padded and the high-value content list is 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 carries the burden of saying what comes back, and it does so by listing the canonical link types. It is complete enough to invoke correctly, missing only a note on what the optional country focus does to the result.

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 country parameter's allowed values are fully enumerated in the schema. The description never mentions the country focus at all, 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 states a specific resource (the GCC Domestic hiring process) and enumerates the payload an agent gets back: country directories, the worker application page, pricing, and verification guides. It is clearly distinguishable from the search_* siblings, though it never names them, so differentiation is implied rather than 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?

"Use this to orient before deeper searches, or to hand a user the right link" gives a clear situational trigger and an output-oriented use case. It stops short of naming which sibling to fall through to (e.g. search_knowledge, search_agencies) when the guide is insufficient.

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, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds genuinely useful behavioral context: monthly publication cadence, provenance (same bands as gccdomestic.com calculator and 2026 salary report), and per-country currency units. It stops short of saying what a response contains or how the guide-link fallback behaves.

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: the first front-loads what the tool returns and its two slicing dimensions, the second adds provenance and currency. Nothing is padding and the most important information leads.

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 has to carry return-value context and it partially does (benchmark bands, per-country currency, monthly cadence). It omits the shape of a band (range/low-high) and the guide-link fallback that the country param mentions, leaving a modest gap for a two-param 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?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not carry: the currency the returned figures are denominated in per country (UAE in AED, Saudi Arabia in SAR). That is real interpretive value beyond the enum-free string params.

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 (get/published benchmarks) and resource (domestic-worker salary bands in the Gulf), with the two scoping dimensions (country, nationality) named. No sibling (get_platform_guide, search_agencies, search_knowledge, search_workers, verify_agency_licence) touches salary data, so an agent can route to this tool unambiguously.

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 use case is implied clearly enough by the resource described, but the description never states when to pick this tool over search_knowledge or get_platform_guide, nor does it surface the fallback path for non-UAE/KSA countries. Usage is inferable rather than guided.

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, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real value beyond that: it scopes the corpus (agencies listed on GCC Domestic across UAE, KSA, Kuwait, Qatar, Bahrain, Oman) and discloses return content (contact details, government-verified flag with a '1,300+ verified' figure, official registry link).

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 and the scope constraint are front-loaded, and the sentence about returns is useful rather than filler. It is a dense single block, though, and the parenthetical enumeration of worker types is the one element that could be trimmed.

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 correctly takes on the burden of describing returns (contacts, verification status, registry link). It leaves minor gaps: the `limit` default of 10 and result pagination are only in the schema, and 'compare' is advertised without explaining what comparison output looks like.

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 the baseline is 3. The description goes beyond the schema by explaining the filter combination logic (country, city and/or free-text name query), noting the query covers English or Arabic, and giving an intent-to-parameter mapping example for `city`.

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 set (find, list, compare) and a precise resource (maid/domestic-worker recruitment agencies), plus the geographic scope (six GCC countries). It also implicitly separates itself from sibling search_workers by targeting agencies rather than workers, and from verify_agency_licence by being a discovery rather than a verification tool.

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 explicit triggering context ('Use this for any "agencies in <place>" question') and a worked example mapping a natural-language phrasing to the `city` parameter. It stops short of naming when NOT to use it or pointing to a specific sibling alternative.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered and the description's 'Read-only' line is largely redundant. It does add value beyond the annotations by disclosing the return shape (title, URL, snippet per result) and the fact that results are URL-bearing, which helps the agent plan how to present or follow up on hits.

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 action and resource in the first clause, followed by a topic list that earns its space by narrowing routing, then two short sentences on output and read-only status. The acronym-heavy topic enumeration is dense but functional; nothing reads as filler.

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 correctly picks up the burden by naming the returned fields (title, URL, snippet) and the read-only nature of the call. What is missing is minor: no indication of how results are ranked or whether the limit cap is a hard ceiling, though the schema already states the 1-5 range.

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%: lang, limit (1-5, default 5) and query (3-500 chars) are all documented in the schema. The description adds only the English+Arabic bilingual scope, which the lang enum already conveys, and says nothing about how limit or query length interact with result quality, 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 (semantic search) and a clearly bounded resource set (GCC Domestic's published guides, blog posts, country pages), with domain examples that make the content scope concrete. It is naturally distinguishable from search_agencies/search_workers/verify_agency_licence by resource type, but it never contrasts itself with the closest sibling, get_platform_guide, so it stops short of full sibling 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?

Usage is only implied: the enumerated topics (visas, Tadbeer/Musaned/PAM procedures, salaries, contracts, refunds, worker rights) tell the agent what kinds of questions belong here. There is no explicit when-to-use, no when-not, and no naming of the alternative get_platform_guide for single-guide retrieval, leaving the routing decision 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 declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value beyond them by disclosing what comes back (public profile info plus the contact agency) and that this tool is not the hiring channel — a downstream-workflow fact an agent could not infer from 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?

Three tight sentences: scope first, filters second, downstream expectation third. No filler and nothing important 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 three-parameter, read-only search with no output schema, the description usefully compensates by describing the return contents and the agency-contact handoff. It could still say something about result ordering or data freshness, but nothing essential to calling 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 description coverage is 100%, with each of the three parameters documented including examples and the limit cap, so the schema carries the burden. The description's 'filter by nationality and/or position' merely restates those fields without adding syntax or matching behavior, 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?

States a specific verb ('Browse') and resource ('domestic workers... available through GCC agencies'), and enumerates the worker categories covered (housemaids, nannies, cooks, drivers, caregivers). This resource is plainly distinct from siblings like search_agencies and get_salary_benchmarks, so an agent can route 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?

Explicitly states the available filter axes ('Filter by nationality and/or position') and frames the tool's place in the workflow ('hiring goes through the worker's agency'). It gives clear context for when to use it but names no alternatives or exclusions, 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 readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: the lookup keys accepted (English/Arabic name, UAE MOHRE facility number, Saudi Musaned reference) and what the result contains (recorded licence status plus a government registry link). It does not address what happens if a name matches multiple agencies, which is a minor remaining gap.

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?

Three sentences, zero filler: scope constraint first, then the accepted lookup keys, then the return contents. Every sentence carries information an agent needs before calling.

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 correctly compensates by stating what is returned (licence status plus official registry link). Annotations cover the safety profile. The only unaddressed case is ambiguous matches when looking up by agency name rather than by number.

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 the baseline is 3. The description goes beyond the schema by explaining that name_or_licence accepts Arabic or English names and by giving concrete registry-specific number examples (MOHRE facility number, Musaned reference), which materially helps the agent construct a correct value.

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 ("Check the licence of ONE specific agency") and immediately draws the boundary against the sibling that could be confused with it ("Not for finding or listing agencies... use search_agencies"). The agent can distinguish this from search_agencies without inspecting either 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?

Explicit when-to-use (single named agency, lookup by name or licence/facility number) and explicit when-not-to-use (finding or listing agencies in a city or country), naming the alternative tool. Nothing is left to inference.

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