headless-oracle

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It goes beyond the basic return type to disclose that results are not cryptographically signed, do not reflect real-time circuit breaker halts or KV overrides, are fail-closed if unreachable, and have sub-100ms p95 latency. It also documents session nuances like lunch breaks and Middle East weekends.

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 long but every section earns its place: purpose, usage triggers, return shape, caveats, and latency. It is front-loaded with the core definition absent any filler, and the labeled sections and bolded callouts make the key operational constraints scannable for an agent.

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 that this tool has a single optional parameter literated in the schema, no output schema, and no annotations, the description compensates fully by enumerating every return field, documenting edge cases, naming sibling alternatives, and stating a fail-closed safety requirement. An agent has everything needed to decide when to call it and what to expect.

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%: the schema fully documents the single 'mic' parameter as an ISO 10383 Market Identifier Code with an enum of 28 values, a default of XNYS, and a pointer to list_exchanges. The description adds contextual examples of specific exchanges and their behaviors, but the core parameter semantics are already fully covered by the schema, so a 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 opens with a specific verb and resource: 'Returns holiday-aware trading session schedule with next open/close UTC timestamps for any of 28 exchanges.' It clearly distinguishes itself from siblings by focusing on schedule computation rather than status verification, and it explicitly names get_market_status as the authoritative alternative.

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?

An explicit 'WHEN TO USE' section lists concrete use cases such as planning trade execution windows and checking holiday closures. It also provides an exclusion: 'NOT cryptographically signed... For authoritative signed status use get_market_status,' and adds a fail-closed directive. This is exceptionally clear routing 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 supplied, the description carries the full burden, and it delivers richly: TTL, fail-closed semantics, statuses, signature field, issuer, latency, live/demo mode, schema version, and the explicit rule that the agent must halt if the tool is unreachable. This exceeds what a safe-read annotation would have provided.

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 heavily over-sized for a one-parameter tool. It repeats the full 28-exchange list already present in the schema enum and includes regulatory citations, a model-agnostic claim, and endorsement disclaimers that do not help an agent select or invoke the tool. While the core safety guidance is front-loaded, the wall of text significantly hurts readability.

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 fully documents the return shape, failure semantics, TTL, cryptographic fields, and the required downstream attestation_ref usage. For a high-stakes pre-trade gate, this is complete enough for an agent to invoke it safely and interpret the result 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%, so the baseline is 3; the schema already defines the MIC enum and provides examples. The description adds meaning by explaining that the receipt is scoped to a specific exchange, listing all 28 MICs with friendly names, and explicitly directing agents to call list_exchanges for discovery. That is meaningful value beyond the raw enum.

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 and resource: it returns an 'Ed25519-signed market-state receipt' for pre-trade verification. It clearly frames the tool as a safety gate across exchanges, which distinguishes it from siblings like get_market_schedule and list_exchanges, and the first sentence alone tells an agent exactly what this tool is for.

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 guidance is explicit and directive: 'call this BEFORE executing any trade' and 'USE AS: pre-trade check, pre-trade verification gate, pre-execution gate'. It also states when NOT to act — UNKNOWN/HALTED must be treated as closed, expired receipts must not be used, and the trade must not execute if the tool is unreachable. This is model-agnostic guidance that leaves no room for 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?

With no annotations, the description carries the full burden. It discloses 'No authentication required' and 'Always returns 200', which are valuable behavioral facts. It also mentions 'Model-agnostic' and lists the return keys, providing transparency about the response shape. No contradictions with annotations exist.

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 labeled sections ('WHEN TO USE', 'RETURNS') and is informative without excessive verbosity. The 'Model-agnostic' sentence is a slight extra but still adds relevant context. Overall, every sentence earns its place.

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-parameter read-only endpoint, the description is quite complete. It covers purpose, usage timing, authentication behavior, HTTP status, and return keys. The lack of an output schema is mitigated by the detailed explanation of the upgrade ladder. It could be more precise about the exact format of the response, but this is sufficient for an 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?

The tool has zero parameters, so the baseline is 4. The description does not need to add parameter semantics, but it does explain the return object structure and provides concrete examples (e.g., sandbox, x402, credits), which adds context beyond the empty 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 'Returns available payment and authentication options for accessing live market data', which is a specific verb+resource. It distinguishes itself from siblings like get_market_schedule and list_exchanges by focusing on payment/authentication rather than market data itself.

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 provides 'WHEN TO USE: when you need to understand how to authenticate or pay before making a request that requires a key or payment.' This gives clear usage context, though it does not mention when not to use or explicitly name alternatives. Still, the siblings are clearly different, so this is strong 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 provided, the description carries the full burden of behavioral disclosure. It states 'Pure static data, always returns 200, no authentication required, sub-50ms p95' and notes the tool is 'model-agnostic.' These details go beyond what any structured field provides and give the agent confidence about safety, performance, and side-effect-free 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 front-loaded with the core purpose and return type, and it uses clear section labels (WHEN TO USE, RETURNS). The exhaustive list of 28 exchanges with MIC codes is informative for a directory tool, but it is longer than strictly necessary and partially duplicates what the tool itself returns. Still, every section serves a distinct purpose.

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?

The description provides the return shape inline, including the nested object structure and mic_type enum values. It also covers usage timing, coverage scope across equities/derivatives/crypto, and behavioral guarantees (200, no auth, p95). For a read-only discovery tool with no annotations and no output schema, this is fully sufficient for correct invocation.

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 has 0 parameters, so the baseline is 4. The description appropriately spends no space on parameters and instead details the output shape. No parameter ambiguity exists, and the schema confirms no inputs are required.

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 and resource: 'Returns directory of all 28 exchanges supported by Headless Oracle.' It enumerates the exact content fields (MIC codes, exchange names, IANA timezones, market hours metadata, mic_type) and distinguishes the tool from siblings by explicitly referencing get_market_status and get_market_schedule later.

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 'WHEN TO USE' section is explicit: 'call once at agent startup to discover supported markets before calling get_market_status or get_market_schedule.' It gives clear timing, purpose, and names the sibling tools it precedes. This leaves no ambiguity about when to select this tool.

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