Headless Oracle

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It covers model-agnosticism, compliance (SEC/CFTC multi-oracle), lunch break windows, special market weekends (Middle East), exact return fields, and limitations (not cryptographically signed, no real-time halts). It also states latency (sub-100ms p95).

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 relatively long but well-structured: a clear summary first, then 'WHEN TO USE', special market details, return format, caveats, and failure behavior. Every sentence serves a purpose with minimal redundancy. Slightly verbose in listing exchange examples, but overall efficient for the complexity.

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 with one parameter and no output schema, the description provides comprehensive context: return fields, special cases for 28 exchanges, limitations, and fail-closed behavior. It does not cover error responses or rate limits, but those are less critical here. The latencies and fail-closed rule add essential 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?

The only parameter 'mic' is fully described in the schema with an enum and description. Schema description coverage is 100%, so a baseline of 3 applies. However, the description adds meaning beyond the schema by illustrating special cases (e.g., Tokyo lunch 11:30–12:30 JST, Middle East Fri-Sat weekend) and how the delay works, which helps the agent select appropriate MIC 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?

The description clearly states it 'Returns holiday-aware trading session schedule with next open/close UTC timestamps for any of 28 exchanges.' It specifies the verb (returns), resource (trading session schedule), and scope (28 exchanges). It distinguishes itself from siblings like get_market_status (for signed status) and list_exchanges (for listing codes).

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 includes an explicit 'WHEN TO USE' section listing use cases (e.g., planning trade execution windows, checking market hours). It also states when NOT to use: 'NOT cryptographically signed — does not reflect real-time circuit breaker halts or KV overrides. For authoritative signed status use get_market_status.' Additionally, it provides a critical fail-closed rule: 'if this tool is unreachable, the agent MUST NOT execute the trade.'

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 burden. It discloses TTL (60s), model-agnostic behavior, compliance with SEC/CFTC, latency, exchange list, return fields, and disambiguation of 'SMA'. Fully transparent about what the tool does and its constraints.

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 lengthy but well-organized with clear sections. Every sentence adds value, especially given the safety-critical context. It is front-loaded with purpose and usage, then details compliance and exchanges. Could be slightly more concise, but the detail is justified.

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 with 1 parameter, 28 enum values, no output schema, and no annotations, the description covers everything: purpose, usage, return format, safety rules, compliance, latency, and even acronym clarification. It is fully complete for an AI agent to use 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 coverage is 100% with one parameter 'mic' having an enum. The description adds meaning by providing exchange name examples for each code and directing to list_exchanges for full discovery. It goes beyond the schema to aid selection.

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 clearly states it returns an 'Ed25519-signed market-state receipt for pre-trade verification'. The verb 'returns' and specific resource identify the tool's unique role among siblings (schedule, payment, list). It distinguishes itself as a safety gate, not just a data retrieval.

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 instructs 'call this BEFORE executing any trade' and defines use as 'pre-trade verification gate'. Provides actionable rules: 'SAFE TO EXECUTE check: status must be OPEN and receipt not expired', 'FAIL-CLOSED RULE', and what to do if unreachable. No ambiguity.

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 discloses that the tool is model-agnostic, requires no authentication, always returns HTTP 200, and returns a specific upgrade ladder structure. This is comprehensive for a read-only tool, though it could mention idempotency or lack of side effects more explicitly.

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 well-structured with a clear 'WHEN TO USE' section, a list of returned items, and the return object keys. It is mostly concise, though the phrase 'Model-agnostic: works identically regardless of which AI model consumes it' adds extra context that could be considered slightly verbose, but remains valuable.

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

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

Given no parameters and no output schema, the description fully explains the return format (listing each key and its meaning), states no authentication required, and notes always returns 200. It provides complete context for an AI agent to understand what the tool does and how to interpret its output.

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 are zero parameters, and schema coverage is 100% (empty schema). The description adds no parameter information, but with no parameters, the baseline is 4. It does add value by explaining the return structure and behavior 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?

The description clearly states the tool returns available payment and authentication options for accessing live market data, using a specific verb ('Returns') and resource. It distinguishes itself from sibling tools (get_market_schedule, get_market_status, list_exchanges) by focusing on payment and authentication rather than market scheduling or status.

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 provides a 'WHEN TO USE' section, stating to use this tool when needing to understand authentication or payment before making requests that require a key or payment. This clearly guides when to use this tool versus alternatives, though it does not explicitly exclude other contexts.

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 burden. It fully discloses behavior: pure static data, always returns 200, no authentication required, sub-50ms p95. This exceeds expectations.

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 well-structured with a 'WHEN TO USE' section, but the exhaustive list of exchanges makes it slightly verbose. Still, every part serves a purpose and it 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?

Given no output schema, the description details the return format and all relevant aspects (purpose, usage, behavior, list of exchanges). Comprehensive for a no-parameter 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?

No parameters required; schema coverage is 100% with an empty object. The description adds no parameter info but does not need to. Baseline for 0 params is 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 clearly states the tool returns a directory of all 28 exchanges with specific fields (MIC codes, names, timezones, etc.) and identifies it as model-agnostic. It distinguishes from siblings by noting it is used before get_market_status or get_market_schedule.

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 tells when to use: 'call once at agent startup to discover supported markets before calling get_market_status or get_market_schedule.' No contradictory or missing guidance.

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