XH Agents Connector (read-only)

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

With no annotations provided, the description carries the burden and discloses important behavior: it is not live, not token-specific, returns already-documented example output, and spends no funds. It does not discuss permissions or rate limits, but for this example-only tool the main side-effect concern is addressed.

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 description is front-loaded with the key distinction that this is an example output, not live scoring. It is somewhat repetitive around 'not live' and 'example output,' but the repetition reinforces an important constraint and does not obscure the main point.

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 the low complexity, one required parameter, no output schema, and no annotations, the description is mostly complete. It explains the return content at a high level (example output plus price) and the main behavioral constraints, though it does not detail the exact response structure.

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 0%, so the description must compensate. It does: the token parameter is described as an EVM address in 0x + 40 hex format and explicitly noted as context only and not evaluated, which is essential semantic information beyond the bare 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 and behavior: it returns a documented example token-safety score output plus price, not a live result or token-specific assessment. It clearly distinguishes itself from the live paid scoring service, so an agent can identify the tool's purpose 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 gives clear when-to-use context: use this to see the documented answer shape, not for live scoring or a specific token. It also states the alternative is a separate paid live service, though it does not explicitly route to any sibling tool such as info_pembayaran or verifikasi_pembayaran.

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?

No annotations are provided, so the description carries the full disclosure burden. It does add real value by naming its grounding sources (Buku Pedoman XH Agents v2, Bagian 5 and 6) and explicitly stating what will not be surfaced — internal paths, file names, addresses, architecture details. However, it never says this is a read-only listing, whether output is per-client or generic, or how results are shaped.

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 one line, followed by the parameter note and then source/boundary constraints. Slightly verbose in the repeated 'tanpa ...' exclusions, but every clause carries substantive meaning.

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 one-optional-parameter, no-output-schema retrieval tool, the description covers what it returns (a checklist), which topics it can return, and its content restrictions. The main residual gap is the response shape, which is not covered by an output schema.

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 0% and the single parameter's schema is an unconstrained anyOf(string, null) with no description. The description compensates well by enumerating the accepted values and defining the null/empty case as 'both', which is information an agent could not get from 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 concrete resource (a general client checklist) and its two subject areas: pre-work preparation and handover. It does not name or contrast any of the sibling tools (payment info, catalog, token-safety example), so an agent must infer that this is the non-transactional, procedural checklist 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?

Usage is implied only through the topik values: 'persiapan', 'serah_terima', or empty for both. There is no statement of when to prefer this over katalog_layanan or info_pembayaran, and no prerequisites or exclusions beyond the content-boundary 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?

With no annotations, the description carries the full disclosure burden. It does add real value: it discloses that the recipient address is read from a single canonical config file and only changes with owner approval (implying this call never mutates it), and it bounds the data returned (no escrow/balance/history/other payer data). However, it never states outright that the call is read-only and side-effect free, and says nothing about auth requirements, freshness/caching, or failure modes.

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 field list in sentence one is efficient, but the second paragraph bundles unrelated concerns (config-file sourcing, privacy exclusions, parameter semantics) into one dense run-on with parentheticals. The only parameter guidance is tacked onto the very end rather than front-loaded, so an agent scanning for 'what do I pass' must read to the bottom.

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 must describe the return payload, and it does so by enumerating the five data points returned. With a single optional parameter and no nested structures, this is close to sufficient. The remaining gap is format-level: it doesn't say how the schedule is shaped when 'paket' is omitted or what the values (network, asset) look 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 coverage is 0% — 'paket' is described only as a nullable integer with default null — so the description must compensate, and it does: 'paket: 1..5 (opsional) untuk jadwal bayarnya' supplies both the valid range and the semantic purpose (selects the payment schedule/package). It does not explain what happens when 'paket' is omitted, which keeps it from a 5.

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 enumerates the exact contents the tool returns (network, asset, recipient address, order number, payment schedule), which is concrete and specific. It also carves out scope with 'Tidak memuat escrow, saldo, riwayat, atau data pembayar lain', which implicitly separates it from verifikasi_pembayaran and katalog_layanan. It never uses an explicit verb ('mengembalikan'/'menampilkan') and never names a sibling directly, so it stops just short of a 5.

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 'call this when you need the official payment destination/order/schedule'. The exclusions (no escrow, no balance, no history, no other payers' data) function as de facto when-not guidance, but no alternative tool or prerequisite is named. There is no explicit 'use verifikasi_pembayaran instead for X' 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?

No annotations are present, so the description carries the full burden — and it does disclose the source ('Buku Pedoman XH Agents revisi v2, Bagian 8'), the data-not-instructions nature of the output, and the exclusion of payment details. It does not explicitly state that this is a read-only, side-effect-free lookup, which is the main 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?

Front-loaded with the core purpose, then source, then output nature, then parameter behavior — four short lines, each earning its place with no redundancy.

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 no output schema, the description supplies the effective return shape (the six enumerated fields), the source, and the scope exclusion. Only the explicit read-only/side-effect statement 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 0% and the single 'paket' parameter has no description, type hints, or enum. The description fully compensates by giving the domain (1..5), the optionality, and the default behavior when omitted (all five packages).

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 ('Daftar 5 paket XH Agents') and enumerates exactly what each entry contains (nama, kondisi awal, isi, harga, jadwal bayar, dukungan). It also explicitly carves itself away from info_pembayaran, so an agent can distinguish it from siblings 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?

Explains the optional-scope behavior ('paket: 1..5 (opsional). Tanpa paket -> kelima paket') and redirects payment questions to info_pembayaran. It stops short of stating when to prefer a specific paket over the full list, but the conditional behavior is explicit.

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?

With no annotations, the description carries the full burden and does so well: it discloses that exactly one request is sent, that no credentials are transmitted, that redirects are not followed, and that only https/443 public hosts are permitted. What it omits is rate-limit or repeat-call behavior and whether failures are reported as errors versus a validation verdict.

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 short lines, front-loaded with the action and the no-payment constraint, followed by the concrete checks and then the url constraints. Every clause adds information; nothing is redundant.

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, no-output-schema diagnostic tool this is nearly complete: the enumerated checks (status 402, payment challenge, x402Version, accepts[], network, asset, payTo format, price consistency) effectively describe what the caller learns back. Only the shape of the result (pass/fail vs structured report) is left implicit.

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 0% and the single 'url' parameter is entirely undocumented in the schema, so the description must compensate — and it does, constraining it to https on port 443 with a public host and no redirect following. That is meaningful semantics beyond the bare 'string' type, though it doesn't explain how a rejected host is reported.

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: send one unpaid request to a public x402 endpoint and inspect the shape of its 402 response. The scope (single request, no payment) is unambiguous. However, it never names or distinguishes itself from the sibling verifikasi_pembayaran or info_pembayaran, so the agent must infer that this validates the *challenge response* rather than a payment.

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: this is clearly a pre-payment diagnostic, and the constraints ('TANPA membayar', 'Tidak mengirim kredensial') signal when it is safe to call. But there is no explicit when-to-use/when-not or routing to alternatives such as verifikasi_pembayaran for actual payment checks.

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?

With no annotations, the description carries the full burden and does well: it declares the operation is read-only, that it is stateless (hash not persisted), and that no balance or history is ever returned. It omits error/negative-result behavior and any confirmation-depth or network-availability caveats, which keeps it below 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?

Front-loaded with the core check in the first line, then the statelessness caveat, then per-parameter notes — every sentence earns its place. The line breaks inside sentences make it slightly ragged, but nothing is redundant.

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 3-parameter tool with no annotations and no output schema, the description covers behavior and parameters thoroughly. The remaining gap is the return shape: it implies booleans for success/address/amount but never says what the response actually contains, which matters given there is no output schema.

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 0%, so the description must compensate and does: tx_hash is specified as 0x + 64 hex, jumlah_usdc as the expected nominal (example 500), and pengirim as an optional payer wallet that, when supplied, constrains the transaction sender. All three parameters gain meaning absent from the bare schema titles.

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: a read-only check of a USDC transaction on Base, verifying success, official recipient address, and sufficient amount. That is far more precise than the name alone and does not overlap with the other siblings (token safety score, checklist, catalog, 402 validation). It does not explicitly contrast itself with any sibling, so it stops short of a 5.

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?

'BACA-SAJA' plus the stateless note implies when the tool is appropriate (one-off payment proof) and gently excludes history/balance lookups. However, it never states when to prefer a sibling such as validasi_respons_402 or info_pembayaran, nor any prerequisite (e.g. transaction already confirmed on-chain).

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