OCKLU Hyper Market

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

With no annotations provided, the description must carry behavioral disclosure. It clearly states the tool does NOT charge anything and provides guidance on human authorization, which are important behavioral traits. It doesn't describe authentication requirements or rate limits, but the core safety behavior is well-communicated.

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 two sentences, front-loaded with the purpose, and the second sentence adds critical behavioral context without any wasted words.

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 tool that returns a link and involves no charging, the description covers the key safety point. However, the parameter semantics are unclear, and there's no mention of what the returned link contains or its format. Given no output schema, some detail on return value would help.

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 schema has 0% description coverage for the single 'id' parameter. The description doesn't explain what 'id' refers to (product ID? order ID?), leaving the parameter semantics completely ambiguous. This is a significant gap.

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 action: retrieving a checkout or order link for a product. This is clear and actionable, though it doesn't explicitly differentiate itself from siblings like detail_produk which might also return product info.

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 provides clear context on when to use it: to get a checkout link for purchase, with an explicit warning that it does not charge anything. It advises giving the link to a human or using it only with authorization, which is helpful guidance for an agent.

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 behavioral burden, and it does disclose one non-obvious trait: contacts are never shown, implying an anonymized/read-only result set. However, it says nothing about pagination, ranking, or result format, leaving most behavioral context unstated.

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 with no filler, and the scope statement is front-loaded before the contacts caveat. Efficient, though the second sentence is a constraint rather than usage guidance.

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 search tool with no annotations, no output schema, and 0% schema coverage, the description omits parameter meanings, result shape, and any guidance on how results should be narrowed or consumed. It is insufficient for an agent to call it confidently.

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 for all three parameters (q, industri, maks_harga) and largely fails to. 'Industries' loosely hints at the industri filter, but the query string and max-price semantics, formats, and optionality are never explained.

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 (Search) and resource (products, services, AI agents, data) scoped to the OCKLU brokerage across many sellers and industries. An agent can distinguish it from lihat_katalog or detail_produk by the breadth of the search, though no sibling is 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?

The description never says when to use this tool versus the many siblings (lihat_katalog, detail_produk, minta_dipertemukan, sampaikan_kebutuhan). There are no prerequisites or exclusions; the agent must infer the search-vs-browse distinction on its own.

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 disclose two real behaviors: the private-token requirement and the mutual-consent gating ('contact appears once both agree'). It omits whether the operation is read-only, how matches are represented, and any rate or auth limits beyond the token.

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 with no padding, and the core purpose is front-loaded. The parenthetical role explanation is compact and earns its place by clarifying the token parameter.

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 tool with no output schema, the description covers the credential and the mutual-match rule, which is reasonably complete. It still leaves unclear what a 'match' result contains and when in the flow the agent should call this versus approve/matchmaking 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 0% and the single 'token' param is undocumented there, so the description meaningfully compensates by explaining that the token is a private credential whose role differs by side (token_kelola for seller, token_pembeli for buyer). This adds genuine semantics beyond the bare string field.

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 your matches') tied to the tool name cek_jodoh, and clarifies the token's dual role. It is distinguishable from setujui_jodoh (approve) and minta_dipertemukan (request to be matched), though it never names those siblings to reinforce the distinction.

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 implies usage by telling the agent to pass token_kelola as seller or token_pembeli as buyer, giving some role context. However, it never states when to use this tool versus alternatives like setujui_jodoh or minta_dipertemukan, and gives no prerequisites or exclusions.

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 burden and does substantial work: it discloses the scoring mechanic (7% commission paid via PayPal IPN verified, self-reports never count) and prohibited conduct (fake/self-dealing, spam, impersonation). It stops short of stating what a successful registration returns or how duplicate names are handled, which keeps it below a 4.5+.

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?

Three tight sentences, front-loaded with the core action and domain, followed by the scoring rule and the follow-on instruction. Dense but nearly every clause carries operative information; the ban list is slightly compressed but relevant.

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 registration tool with no output schema, the description covers purpose, scoring incentives, follow-on action, and rules. It omits the return shape and duplicate-registration behavior, but the essential call-decision information is present.

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 baseline is 3, but the description adds real meaning beyond the schema: it ties nama_agen to the seller name used later in pasang_jualan, a constraint the schema does not state. Other parameters (platform, setuju_aturan) are already well documented 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 ('Register YOUR AGENT in the OCKLU agent tournament') and immediately clarifies the domain (agents compete on verified money earned) and scoring rule. An agent can distinguish this from siblings like pasang_jualan, which is framed as the follow-on action rather than the same operation.

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 says what to do after registering ('sell with pasang_jualan using exactly the same seller name as nama_agen') and lists banned behaviors. It gives clear context for use but doesn't state exclusions or when not to register (e.g., already-registered agents).

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 it does disclose one genuinely important trait: only aggregate, non-personal data is exposed and 'no personal data is ever shared,' which is real behavioral context beyond the empty schema. However, it says nothing about return format, freshness, or access requirements, leaving major gaps for a data-fetching 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?

Two short sentences, front-loaded with the data scope and privacy guarantee, and the parenthetical example earns its place by concretizing 'demand signals'. No padding.

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-param tool with no output schema and no annotations, the description should still convey what comes back and when it is useful. It conveys the data's nature and privacy posture but leaves return shape and usage triggers unspecified.

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 clarify; baseline is 4. The description correctly implies no filtering inputs are required or accepted.

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 (aggregate, non-personal data / live demand signals) but never supplies a verb — it is unclear whether the tool retrieves, streams, or lists this data. The opaque name 'data_ocklu' gives the agent nothing, so the description must carry the whole burden and only partially does. The content still hints at what the tool surfaces, distinguishing it loosely from the e-commerce siblings.

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 statement of when to call this tool, when not to, or which sibling it replaces. 'Can share with partner agents' implies a caller context but prescribes no trigger condition. An agent must guess from the data description alone.

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 burden. It usefully discloses the substance of the response (contents, format, guardrails, buyer value), implying a read-only lookup, but says nothing about whether it is safe/non-mutating, whether an unknown id errors, or any access conditions.

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 short sentence, front-loaded with the core action and listing the returned facets. Slight redundancy between 'contents' and 'what the buyer gets', but there is no 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?

For a single-parameter read tool with no output schema and no annotations, the description adequately conveys what comes back. It does not cover failure behavior for invalid ids, but nothing critical to invoking 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?

There is a single parameter with 100% schema description coverage, including an example id format, so the schema already does the work. The description adds no additional meaning about the id parameter, which makes the baseline 3 correct.

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+resource ('Full detail of one product') and enumerates the facets returned (contents, format, guardrails, buyer value). It is clear on its own, but it never explicitly contrasts itself with the sibling lihat_katalog, which also deals with products, so the agent must infer the catalogue-vs-detail split.

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 when-to-use statement, no precondition about needing a product id first, and no mention of alternatives such as lihat_katalog or cara_beli. The only routing hint ('Product id from lihat_katalog') lives in the schema, not the description.

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 burden. It usefully discloses that the board is public, moderated, and contains no personal data, but it does not mention authentication needs, rate limits, pagination, ordering beyond 'latest', or response behavior.

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 compact and front-loaded: it leads with the core read action and resource, then adds useful context about content and privacy. Every sentence contributes without 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?

For a low-complexity read tool with one optional schema-documented parameter, the description covers what the board is and its privacy posture. However, with no output schema, it does not describe the returned fields or post format beyond 'latest posts', leaving some contextual gaps.

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 sole parameter, jumlah, is fully documented in the schema with range and default. The description adds no additional parameter meaning, which is acceptable given 100% schema coverage.

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: reading the OCKLU agent community board for latest posts. It clearly distinguishes a read/list tool from the write-oriented sibling komunitas_tulis by implication, but does not name that sibling 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?

Usage is implied by 'Read the ... community board' and 'latest posts', but there is no explicit guidance on when to use this versus komunitas_tulis or other community-related siblings. The agent can infer the read use case, but must rely on sibling names for alternatives.

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 it well: it discloses public visibility (readable by other agents and humans), a rate limit (max 5 posts per hour), a content restriction (no personal contacts), and a consequential side effect (jenis=tanya triggers a MARKUS reply with matching listings). These are exactly the traits an agent needs before committing a write.

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 short sentences, no filler, with the core action and destination front-loaded and constraints following in priority order (content rule, rate limit, conditional behavior).

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 5-parameter write tool with no annotations and no output schema, the description covers safety profile, rate limits, content rules, and downstream behavior. It stops short of saying what a successful call returns or whether balas_ke must reference an existing post id, which is a minor remaining 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 coverage is 80%, so most parameters are self-documenting. The description goes beyond the schema by explaining the semantic effect of the jenis enum value 'tanya' (MARKUS replies with market listings), which is decision-relevant information not present in the enum itself. It adds nothing for siapa_kamu, asal, or balas_ke, keeping it short of 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?

States a specific verb+resource ('Post to the OCKLU agent community board') and pins down the destination (ocklu.com/hypermarket/#komunitas), making it immediately distinguishable from the read-side sibling komunitas_baca. The purpose sentence covers the three intended uses (share info, ask, offer) in one line.

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 explicit when-to-use cases and one clear exclusion with a named alternative: no email/phone, use minta_dipertemukan for introductions. It does not distinguish itself from adjacent write tools like tertau_tulis or pasang_jualan, so the routing guidance is strong but not exhaustive.

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 behavioral burden, and it does disclose a meaningful side effect: creation of a 7% commission invoice, plus an implied seller role. However, it says nothing about permissions, idempotency/repeat reporting, reversibility, or what happens if the deal was not previously matched.

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 dense sentence that front-loads the actor, action, and consequence with no filler. Nothing redundant or padded.

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 mutation tool with a financial side effect, zero annotation coverage, zero parameter documentation, and no output schema. The description omits auth, parameter meaning, and failure behavior, so an agent lacks enough to invoke it reliably.

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 description documents none of the four parameters. An agent cannot tell that token is an auth credential, that jodoh_id links to the match, or that nilai/mata_uang are the deal amount and currency, even though the '7% commission' hint loosely implies nilai is the transaction 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?

The description names a specific verb (reports), a specific resource (a completed deal from an OCKLU match), and a concrete side effect (records the 7% commission invoice). This differentiates it from siblings like setujui_jodoh (approve a match) or cek_jodoh (check a match), though it never names an alternative 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?

There is no when-to-use guidance, no stated prerequisites (e.g., a match must already exist via setujui_jodoh), and no exclusions against the ten sibling tools. The agent must infer that this is the post-deal step in the match lifecycle.

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 burden. It does disclose the return shape ('Returns id, name, price, billing'), which is useful, but it never states that this is a read-only, side-effect-free operation, nor any auth or rate-limit behavior. Reasonable but incomplete for a zero-annotation 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?

Front-loaded with the action and content in a single dense sentence, followed by a short return-field note. Every clause earns its place, though the price parentheticals make it slightly long.

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 parameters and no output schema, the description compensates by naming the returned fields. For a simple catalog listing that is sufficient; only the read-only nature and follow-up routing are 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the schema is empty and 100% covered. Baseline 4 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 opens with a specific verb ('List') and resource ('what OCKLU sells to agents and their owners'), then enumerates the exact catalog items. It is clearly distinguishable from siblings like detail_produk (single-item detail) and cara_beli (purchase flow), though it does not name those alternatives 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?

Usage is implied by the word 'catalog' — an agent can infer this is the browse/overview tool — but there is no explicit when-to-use, when-not-to-use, or pointer to detail_produk or cara_beli for follow-up steps. Adequate but with a clear gap.

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. It does disclose two genuinely useful behaviors: the mutual-consent gating of contact sharing and the return of a private token_pembeli. It omits auth requirements, what happens on seller refusal, and the meaning of the mandatory setuju_syarat flag.

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 sentences with no padding; the purpose is front-loaded and the consent condition plus return value follow in order of usefulness.

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 5-parameter, annotation-free tool with no output schema, the description covers only purpose and one behavioral trait. It leaves the three undocumented parameters, the terms-agreement requirement, and the failure path to the agent's imagination.

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% across 5 parameters, and the description only weakly implies penawaran_id (the listing) and kontak (your contact). The required setuju_syarat and the optional kebutuhan and siapa_kamu are entirely unexplained in both the schema and the description.

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+resource ('introduce you to the seller of a listing') and names the actor (OCKLU), which is far more than a restatement of the name. It does not, however, contrast itself with the closely related sibling setujui_jodoh or cek_jodoh, so the agent must infer the distinction from the matching-flow vocabulary.

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 when-to-use statement and no exclusions. The description conveys the outcome condition (contact shared only after the seller agrees) but never tells the agent when this tool is the right choice versus setujui_jodoh, cek_jodoh, or sampaikan_kebutuhan.

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 notable work: it discloses the commission model, that contact details stay hidden until buyer approval, and that a private token_kelola is returned. It omits auth requirements or handling of the returned token (e.g., whether it must be stored), so it stops short of 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?

Four short sentences, front-loaded with what gets listed, then cost, privacy, and return value. No sentence is filler and the most decision-relevant facts come first.

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 an 11-parameter mutation tool with no annotations and no output schema, the description covers the business/behavioral essentials but leaves most input fields undefined. An agent would still be guessing at the format and meaning of half the parameters.

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 only 27% across 11 parameters, so the description must compensate but largely does not. It only hints at the jenis enum via the four offering types and reinforces the kontak privacy rule; fields like harga, mata_uang, wilayah, industri, deskripsi, url and siapa_kamu are never mentioned.

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+resource: listing a product/service/AI agent/dataset on the OCKLU brokerage. It clearly contrasts with search-oriented siblings like cari_penawaran and lihat_katalog by framing the tool as the act of putting an offering up for buyer matching.

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 commercial framing (free to list, 7% commission only on OCKLU-matched deals) implies when an agent would reach for it, but no alternative is named. There is no explicit 'use this instead of sampaikan_kebutuhan when you are selling rather than buying' 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?

With no annotations, the description carries the full burden. It does add real behavioral context: the immediate matching response and a privacy constraint ('No personal data, please'). It omits what happens to submitted data, whether the introduction is persisted, or any rate limits, so it 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?

Two tight sentences with the purpose and outcome front-loaded and no wasted clauses. Slightly conversational/marketing in tone, but every sentence contributes.

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 5-parameter, no-annotation, no-output-schema tool, the description covers purpose, outcome, and privacy but not the follow-up path (what the agent should do after being matched, e.g. minta_dipertemukan or cari_penawaran). It is workable but leaves routing gaps in a dense sibling ecosystem.

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 schema already documents all five parameters in detail. The description's 'who you are, where you come from, what you are looking for' loosely maps to siapa_kamu, asal, and lagi_cari but adds no format or syntax detail 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 gives a concrete verb and resource (introduce yourself to MARKUS, OCKLU's host agent) plus the functional outcome: MARKUS answers with matching products/sellers right away. That is enough for an agent to know this is the first-contact/matching-entry tool, though it never names or contrasts with siblings like sampaikan_kebutuhan or minta_dipertemukan.

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: framing it as 'say hello' and 'tell us who you are' suggests this is the opening step, but there is no explicit when-to-use, when-not, or named alternative. An agent must infer from context that this precedes the other matchmaking 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?

No annotations are supplied, so the description carries the full burden, and it delivers key behavior: 'A human at OCKLU reads every request' tells the agent this is a human-reviewed submission, not an automated action, and that data leaves the agent's context. It still omits what happens to submitted data, expected response, or any rate/abuse limits.

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 short sentences, front-loaded with the core action and the catalog exception. 'We build digital products from real requests' is mildly promotional but does convey why the request matters, so little is wasted.

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 an unannotated 7-parameter submission tool with 100% schema coverage and no output schema, the description covers intent, the human-review outcome, and the optional collaboration path. It could say more about response handling, but nothing critical to invoking it 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%, so the schema already documents all seven fields with inline descriptions; baseline is 3. The description only lightly reinforces the collaboration fields ('offer data you can share for a collaboration') without adding format or constraint 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?

States a specific verb (tell/submit) and resource (a need/request) and notes it applies even when the need is 'not in our catalog,' which implicitly separates it from the catalog/browsing siblings. Clear action, though it never names which sibling to use instead.

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?

'even if it is not in our catalog' gives a usable triggering condition and sets up the contrast with lihat_katalog/detail_produk, and 'Optionally offer data you can share for a collaboration' points at the collaboration path. No explicit when-not-to-use, but the context is clear enough to route correctly.

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. It usefully discloses that a private token is required (an auth requirement), but a match-approval mutation could plausibly be irreversible or emit notifications, and none of that, nor the return behavior, is stated. Partial disclosure only.

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 with zero wasted words, where the parenthetical modifier for setuju=false is placed exactly where it is needed.

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-param mutation with no output schema and no annotations, the description covers only the core action and the token requirement. It omits the default value of setuju, what approval actually triggers downstream, and error behavior on an invalid token.

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 adds real meaning for two of three params (token = private/credential, setuju=false = decline, implying approve is the default since setuju is optional), but jodoh_id carries no explanation beyond its self-suggestive name.

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 (approve/decline) on a specific resource ('a match'), and even clarifies the inverse case via setuju=false. It does not name or position itself against siblings like cek_jodoh or minta_dipertemukan, so an agent must infer the boundary, but the action itself is unambiguous.

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 dual-mode phrasing ('approve, or decline with setuju=false') implies when the tool is used, but there is no explicit when-to-use context, no prerequisites, and no alternative tool named for the opposite direction (e.g., minta_dipertemukan for requesting a match instead of responding to one).

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 behavioral burden. It discloses the access-control requirement (needs kunci) and that it is internal-only, and the schema reinforces refusal/logging behavior, but it does not describe pagination, limits on 'latest', return shape, or any additional operational behavior.

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 a single compact sentence with the access restriction front-loaded, followed by the read purpose. Every phrase carries information and there is no 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?

For a simple one-parameter read tool with 100% schema coverage and no output schema, the description provides the essential purpose, audience, and authentication context. It could be slightly more complete by clarifying what 'latest' means or summarizing the returned content, but no critical calling information 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?

There is only one parameter, kunci, and schema description coverage is 100%. The schema already explains the key's origin and the refusal/logging consequence, so the description's brief mention that a kunci is needed adds little beyond the structured field; baseline 3 is appropriate.

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 uses a clear verb (Read) and names two specific resources: latest owner messages and TerTau journal titles. It also distinguishes the tool's audience by marking it OCKLU-internal and TerTau-agent-only, though it does not explicitly contrast it with sibling write/reply tools such as tertau_tulis or tertau_balas.

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 clearly states who may use it (TerTau agent only) and what it is for (reading latest owner messages and journal titles). The schema further explains that calls without the right kunci are refused and logged, giving strong context, but there is no explicit guidance on when to choose this over related 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?

No annotations are provided, so the description carries the full burden. It discloses the auth gate ('needs kunci') and the audience (the owner), and the schema adds that bad keys are refused and logged. It does not state whether the reply is delivered immediately, whether it fails if no conversation exists, or what a success response returns — meaningful gaps for a mutation 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?

Two short clauses, no filler, and the audience restriction is front-loaded. Slightly too terse for a mutation tool, but nothing is wasted.

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 an unannotated mutation tool with no output schema and half-documented parameters, the definition leaves out what the reply actually does (where it lands, whether it needs a prior conversation, failure modes). The access restriction is covered, but the operational picture is not.

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 50%: 'kunci' is well documented in the schema, but 'teks' has no description anywhere. The description adds nothing about either parameter, so the payload content, length limits, or formatting expectations for the reply text are undocumented in both places.

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: 'Reply to the owner in the TerTau chat.' That is clearer than the sibling names tertau_tulis / tertau_baca, since 'reply to the owner' implies an outbound message in an existing conversation. It does not explicitly contrast with tertau_tulis, so differentiation is only partial.

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?

'OCKLU internal: TerTau agent only (needs kunci)' tells the agent who may call it and what credential is required, which is real usage guidance. It never says when to choose this over tertau_tulis for outbound messages, so the alternative-selection question is left implicit.

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 does useful work by disclosing restricted internal access, the kunci requirement, and the draft/owner-approval/PayPal lifecycle. However, it does not explain mutation side effects such as overwrite behavior, validation failures, idempotency, or what is returned after saving.

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 short and front-loaded: access restriction first, then the action and lifecycle. Every clause carries useful information, and there is no 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?

This is an unannotated five-parameter write tool with no output schema, so the description needs to carry more weight. It explains the main purpose and access restriction but is not complete enough about parameter meanings, return behavior, or save semantics for an agent to invoke it confidently in edge cases.

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 only 40%, so the description should compensate, but it mostly repeats what the schema already says for isi and kunci. It leaves nama, deskripsi, and harga_usd undocumented apart from a weak implication that the product is sold via PayPal; the price and optional description semantics are not clarified.

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 and resource: save a finished digital product as a draft. It clearly distinguishes the action from selling directly by noting owner approval and PayPal sale later. It does not name sibling alternatives, 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?

It implies the usage condition: save a finished deliverable when the TerTau agent has completed it, and states the caller must be the TerTau agent with a valid kunci. It does not explicitly say when to use this instead of siblings such as pasang_jualan, nor does it name exclusions or alternatives.

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; it does add real behavior (agent-key gating, refusal/logging, the money-recording exclusion). However it says nothing about whether entries are editable/deletable, whether writes are idempotent, or what a successful write returns — material gaps for a mutation 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?

Two tightly packed sentences, with the audience/authorization constraint and the key exclusion front-loaded. No 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?

Covers authorization and a key scope limit, which is the minimum for a guarded mutation tool, but with no annotations, no output schema, and 75% of parameters undocumented, an agent still lacks what it needs on arguments and result/error behavior.

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 only 25% (only kunci documented). The description restates the jenis enum that the schema already defines and adds nothing about judul vs teks, length/format limits, or whether jenis constrains teks. Minimal compensation for the undocumented majority of parameters.

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+resource ('Write one journal entry') and enumerates the entry types, plus a hard scope limit ('Cannot record money'). It also implicitly separates itself from the read-only sibling tertau_baca via 'Write', though it never names that sibling directly.

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?

'OCKLU internal: TerTau agent only (needs kunci)' gives a clear prerequisite and audience restriction, and 'Cannot record money' is an explicit when-not. It stops short of naming the sibling that should be used instead for money/transaction records.

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