headless-oracle

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

No annotations provided, so description carries full disclosure burden. Excellent coverage: discloses lunch break windows for specific exchanges (Tokyo, Hong Kong, Shanghai), Middle Eastern weekend patterns (Fri-Sat), 24/7 crypto markets, latency characteristics ('sub-100ms p95'), and critical limitations ('NOT cryptographically signed', no circuit breaker data).

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?

Uses structured headers (WHEN TO USE, RETURNS, NOT, LATENCY) for scannability. Front-loaded with core purpose. Slightly verbose in RETURNS section (inline JSON-like structure) but every section provides distinct value (limitations, latency, regional market quirks). Could be tightened but earns its length.

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?

No output schema exists, but description compensates with detailed RETURNS documentation covering all fields (mic, name, timezone, timestamps, lunch_break, settlement_window). Addresses edge cases (holidays, early closes, different weekend patterns across 28 exchanges). Complete for a market schedule tool.

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

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

Input schema has 100% description coverage with enum values documented. Description mentions '28 exchanges' and references list_exchanges, but adds minimal semantic value beyond the schema's explanation that MIC defaults to XNYS and that list_exchanges shows supported codes.

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 specific verb 'Returns' and clearly identifies resource as 'holiday-aware trading session schedule with next open/close UTC timestamps' for '28 exchanges'. Distinguishes scope by mentioning specific exchanges, lunch breaks, and different weekend patterns (Middle East, crypto).

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?

Contains explicit 'WHEN TO USE:' section listing six specific scenarios (planning execution windows, checking holiday closures, early closes, etc.). Critically, names sibling tool 'get_market_status' as alternative for 'authoritative signed status', providing clear decision criteria.

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 provided, so description carries full disclosure burden. Extensively documents: TTL (60s), latency SLA (sub-200ms p95), cryptographic attestation chain (Ed25519 signature for x402 downstream flows), fail-closed safety semantics, and live/demo mode distinction. Covers operational, security, and integration behavior comprehensively.

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 critical safety instructions (FAIL-CLOSED RULE) before technical details. Structured with clear section headers (USE AS, RETURNS, LATENCY, EXCHANGES). Length is justified by safety-critical nature and 28 exchange enumerations, though some redundancy exists between RETURNS block and earlier prose.

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?

Compensates fully for missing annotations and output schema. Documents return structure inline (receipt_id, signature, status enum), downstream integration patterns (x402 attestation_ref), temporal constraints (expires_at), and complete exchange coverage. Appropriate for a cryptographic safety gate with complex compliance requirements.

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 has 100% coverage on the single 'mic' parameter, establishing baseline 3. Description adds substantial semantic value by mapping all 28 MIC codes to human-readable exchange names (XNYS=NYSE, XNAS=NASDAQ, etc.) and clarifying domain context ('Equities', 'Derivatives', 'Crypto 24/7').

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 specific verb ('Returns'), resource ('Ed25519-signed market-state receipt'), and scope ('28 global exchanges'). Distinguishes from siblings like list_exchanges (discovery vs. status retrieval) and verify_receipt (verification vs. generation) by emphasizing its unique role as a pre-trade safety gate.

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 prescribes usage with 'USE AS: pre-trade check... call before any financial execution' and mandates 'SAFE TO EXECUTE check: status must be OPEN'. Defines fail-closed semantics ('UNKNOWN and HALTED MUST be treated as CLOSED — halt all execution immediately') which constitutes clear when-not-to-proceed 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?

No annotations provided, but description fully compensates by disclosing: (1) 'No authentication required' - auth requirements, (2) 'Always returns 200' - error handling behavior, (3) Detailed return structure with specific pricing tiers and limits. Excellent behavioral disclosure.

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

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

Four dense sentences using structured headers (WHEN TO USE, RETURNS). Every sentence earns its place: purpose, usage context, return payload details, and auth/error behavior. No redundancy or 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?

No output schema exists, so description must explain return values—and does so explicitly by listing the return object structure and detailing all payment tiers/pricing. Covers all necessary context for a zero-parameter information-retrieval tool.

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

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

Input schema has 0 parameters. Per rubric, 0 params = baseline 4. Description correctly does not invent parameter semantics where none exist, matching the empty schema appropriately.

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 specific action (Returns) + resource (payment and authentication options) + context (for accessing live market data). Clearly distinguishes from sibling tools like get_market_status or list_exchanges by focusing on payment/auth rather than market data.

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

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

Explicit 'WHEN TO USE' section states exact scenario: 'when you need to understand how to authenticate or pay before making a request that requires a key or payment.' This clearly differentiates from tools that actually fetch data or verify receipts.

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 provided, but description fully compensates by disclosing: pure static data nature, reliability ('always returns 200'), authentication requirements ('no authentication required'), and performance characteristics ('sub-50ms p95'). Also details exact return structure.

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?

Well-structured with clear sections (description, WHEN TO USE, RETURNS). Front-loaded with main purpose. Exchange enumeration is lengthy but serves as valuable reference data. Only minor deduction for length relative to essential information density.

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?

Comprehensive despite no output schema in structured fields: documents return structure, shape, and field types in description. Covers auth, performance, reliability, and enumerates all 28 supported exchanges with MIC codes. No gaps evident.

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?

Input schema has zero parameters. Baseline score is 4 per rubric for 0-parameter tools. Description implicitly confirms no inputs needed by describing it as a static discovery call, though does not explicitly discuss parameter absence.

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?

Excellent specific description: 'Returns directory of all 28 exchanges supported by Headless Oracle' specifies exact resource and scope. Clear sibling differentiation by referencing get_market_status and get_market_schedule as tools to call after this discovery step.

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

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

Explicit 'WHEN TO USE' section states 'call once at agent startup to discover supported markets before calling get_market_status or get_market_schedule.' This provides clear temporal guidance and prerequisite relationship to 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, yet the description comprehensively discloses: latency characteristics (sub-50ms p95), execution environment (in-worker, no external network calls), security failure rules (valid=false MUST be treated as untrusted), state combinations (valid=true with expired=true), and recovery actions (re-fetch if expired).

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?

Well-structured with clear section headers (WHEN TO USE, RETURNS, FAILURE RULE, LATENCY) and front-loaded purpose statement. Slightly verbose but justified given the lack of output schema and annotations—every section provides necessary behavioral or integration context that structured fields omit.

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?

Excellent compensation for missing structured metadata: documents the complete return object structure (valid, expired, reason enums, mic/status/expires_at fields), spells out acronym disambiguation (SMA), and includes critical security warnings necessary for a cryptographic verification tool in a financial/trading context.

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% for the single 'receipt' parameter. The description adds valuable semantic context beyond the schema: it clarifies the parameter originates from 'get_market_status' (sibling tool) and specifies the signature encoding (hex-encoded Ed25519), which aids in proper invocation.

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 (Verifies the Ed25519 cryptographic signature) on a specific resource (Headless Oracle Signed Market Attestation receipt) and distinguishes from sibling get_market_status by noting the receipt is 'as returned by get_market_status'—this clarifies that get_market_status fetches while this tool validates.

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?

Contains an explicit 'WHEN TO USE' section with three specific scenarios: (1) confirming pre-trade attestations from other agents, (2) building audit trails for capital commitment workflows, and (3) confirming verification before x402 payment attestations. This provides clear guidance versus alternatives.

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