Oxaide — Singapore company research for AI agents

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

Annotations only declare the generic write/open-world/non-idempotent profile, while the description adds high-value behavior: an immediate job id return, an asynchronous emailed quote (~15m), the S$390 pack price, the human-quote escalation path, and the payment prerequisite before work begins. This is exactly the operational context an agent cannot infer from the hints.

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, each carrying new information, with the identity and immediate return front-loaded before pricing and payment constraints. No redundant restatement of the tool name or schema, though the '$390 Pack' phrasing is slightly compressed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by stating the return value (a job id) and the asynchronous email follow-up, plus cost and payment gating for a write tool. It is essentially complete for a submission tool, with only the absence of failure/validation behavior as a minor 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 description coverage is 100%, so brief, email, and source are already fully documented in the input schema. The description only reinforces the email-first delivery model implicitly and adds no syntax or format detail beyond the schema, making the baseline 3 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?

States a specific verb and resource ('Create a private research job (Oxaide)') and names the product, which immediately separates it from read-only siblings like get_audit and list_audits. The scope ('private research job') is concrete enough for an agent to know exactly what is being created.

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 downstream sequencing ('Pay with pay_audit before any work starts') and clarifies the pricing tier boundary ('Bigger than a pack is human-quoted fixed by email'), which routes the agent to the right follow-up tool. It stops short of saying when this is preferable to a cheaper sibling like lookup_ownership, so there is a minor gap in exclusion guidance.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructiveness. The description adds value beyond that by revealing the specific data returned (status, pricing, payment state, delivery state) and by framing the tool as a polling mechanism, which is useful behavioral context for an agent.

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 contain all essential information: what the tool returns and when to use it. No filler or redundancy; information 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?

For a simple single-parameter getter with strong annotations, the description is largely sufficient. It covers purpose, return fields, and usage timing. A minor gap is not distinguishing from get_audit_result, but the field list provides enough differentiation for most 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 100%, and the parameter 'id' is already well-described as the job id returned by create_audit with format brief_xxx. The description does not add further param-specific meaning, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Get'), a single resource ('one job'), and the exact fields returned (status, quoted tier/price, payment state, delivery state). This clearly differentiates it from siblings like list_audits (plural), create_audit (creation), and pay_audit (payment), and the title reinforces its purpose.

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 explicitly says 'Poll after create_audit', giving clear temporal context for when to invoke the tool. It does not explicitly name alternatives or exclusion cases (e.g., when to use get_audit_result instead), 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, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral context beyond annotations: the result is a markdown summary, and files are delivered asynchronously via email and status page. No contradiction with 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?

One clean sentence with the core action front-loaded and a compact parenthetical clarifying the expected result. No wasted words or redundant restatement of the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter, read-only tool with full schema coverage and annotations, the description is largely complete: it names the resource, the output format, and the delivery mechanism. The main gap is not explicitly explaining when the delivered pack becomes available or how this tool relates to get_audit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single required parameter 'id' is already described as 'Job id'. The description does not add extra parameter-level detail, which matches the baseline for fully documented 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?

The description uses a specific verb ('Get'), a specific resource ('delivered answer/pack for a job'), and concrete content details ('markdown summary; files arrive by email + status page'). It clearly identifies a retrieval operation and distinguishes this from a generic audit fetch.

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 via the word 'delivered' and the mention of email/status-page delivery, suggesting it is for retrieving a completed result. However, there is no explicit guidance about when to use this tool versus siblings like get_audit, nor any when-not-to-use conditions.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: admin_token must match the server MCP_ADMIN_TOKEN and is disabled when unset, plus an explicit statement that the tool is never public. This goes beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact sentence that front-loads the action and restriction. It is efficient and free of filler, though the terminology mismatch ('jobs' vs 'audits' vs 'Briefs') slightly detracts from structural clarity.

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 list tool with two parameters and no output schema, the description covers auth and access scope but does not describe the return format or clarify what 'jobs' refers to. The terminology ambiguity leaves some gaps, though the annotations handle the safety profile.

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 adds meaning for admin_token by specifying it must match the server token and is disabled when unset, which is more detail than the schema's 'Admin token (MCP_ADMIN_TOKEN)'. This extra semantic context justifies a 4.

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 'Admin only: list recent jobs', which is a clear verb and resource, and the admin restriction helps distinguish it from public tools. However, the term 'jobs' conflicts with the tool name 'list_audits' and the title 'List recent Briefs (admin)', creating terminology inconsistency that prevents a perfect score.

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 access context ('Admin only', 'Never open to the public') and the token requirement, but it does not explain when to use this tool versus siblings like get_audit or get_audit_result. Usage is implied rather than explicitly contrasted with 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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the lookup is free and instant, and the data comes from a monthly register snapshot (staleness), plus an explicit statement of what is excluded. It stops short of auth or rate-limit detail, so a 4 rather than 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the return scope before the limitation and the routing instruction. Every clause earns its place: capability, data source, exclusion, and alternative tool with its argument template.

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?

There is no output schema, so the description compensates by enumerating the returned fields and stating the data source. For a single-parameter read tool whose annotations carry the safety profile, nothing needed to call 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% and the single parameter already carries an example UEN format, so the schema does the heavy lifting. The description names the UEN but adds no syntax, format, or validation meaning beyond what the schema provides, making 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 (lookup) and resource (Singapore entity by UEN) and enumerates exactly what is returned: registered name, status, entity type, registration date. It also distinguishes itself from the ownership-chain path via create_audit, so an agent can separate it from its siblings without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly gives the when-not and the alternative: officers and shareholders are NOT in the free snapshot, and the ownership chain requires create_audit with a specific query string. It even supplies the exact argument pattern ('Ownership of <name> (<uen>)'), removing all 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 describe the operation as readOnly=false/openWorld=true/idempotent=false, and the description harmonizes with that by disclosing the two-phase payment flow and the critical rule that work starts only after payment is verified AND settled. It also explains what each method returns and the header/meta requirement for settlement — substantial behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences front-load the core action and then pack the payment flow details efficiently. There is no filler, and every clause adds operational value.

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?

Despite having no output schema, the description states what each method returns and gives the settlement steps an agent must take. Combined with the schema's id and method definitions, an agent has enough information to drive the payment flow correctly.

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 covers 100% of parameters, giving the baseline 3. The description adds meaningful method semantics: stripe returns a Stripe Checkout URL and x402 returns v2 payment requirements on Base, plus which method is default. 'id' is not elaborated beyond the schema's 'Quoted job id,' but the schema already covers it.

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?

Description opens with 'Pay a quoted job,' a specific verb+object that clearly identifies the operation. It then distinguishes between stripe and x402 payment paths, and the name/title align with the action.

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 provides clear usage context: pay only a 'quoted job,' and use stripe vs x402 based on desired payment method. It explains the two-step settlement for x402, but no sibling tool is a payment tool, so there are no explicit when-not-to-use 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?

Annotations only give the generic readOnly/openWorld/idempotent/destructive profile; the description adds real context: async delivery via email and status page, ~5 min latency, one ping consumed per call (implying non-idempotent credit spend), and the requirement that the delivery email match the purchase email (tags allowed). It does not say what happens on failure or whether a failed run still burns a ping.

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, scoping and prerequisites front-loaded. The packed parentheticals (price, duration, delivery channels, URL) are useful but slightly dense, keeping it short of a perfect 5.

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 and all 3 required params documented in both schema and description, nothing an agent needs is missing: cost, latency, delivery channel, authorization artifact, and how to obtain one are all 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 the 3-param baseline would be 3. The description goes further by explaining the provenance and format of pack_id (pp_xxx from the purchase email), that possession authorizes the redeem, and the email-match constraint (+tags ok), which is meaning beyond the schema text.

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 ('Run one prepaid registry ping') plus the delivery mode (email + status page). An agent can distinguish this from the audit-oriented siblings (create_audit, get_audit) immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear prerequisites (a pack_id from a ping-pack purchase) and a fallback path when none exists (POST /api/brief/ping-pack first). It stops short of naming sibling tools or stating when a full audit is preferable to a ping, so it is not a full routing guide.

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?

Goes well beyond the annotations by disclosing the payment mechanism (Stripe, cards + PayNow), the activation condition ('activates on payment'), and the 12-month prepaid term. It stops short of warning that no subscription exists until payment completes or what happens if checkout is abandoned — relevant given idempotentHint=false.

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-loads the action and the price table in two dense sentences with no filler. The inline price list is long but each item is functional information an agent may need to present to a user.

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 explains what is returned (checkout URL) and when the watch becomes active, which is the key missing piece. Minor gaps: whether re-invocation creates duplicate checkouts, and which plan key corresponds to which price.

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 already a 3; the description adds real value by mapping plan choice to price points and restating that the target plus a delivery email are required. The mismatch between prose plan names and schema enum values slightly weakens that mapping.

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 ('Start a prepaid 12-month Watchdesk watch') plus the concrete outcome ('Returns a Stripe checkout URL'), which clearly separates it from sibling tools like create_audit and pay_audit. The one weakness: the plan labels in the prose (business-name, IPOS-filing) do not match the schema's plan values (trademark, ipos-watch), so the pricing list is not directly mappable to a call.

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 agent can infer this is the purchase path rather than the audit-creation or audit-payment path. There is no explicit 'use this instead of pay_audit when...' statement and no preconditions (e.g. whether a target must be validated first).

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