Real-time SPX (0DTE) options dealer market-structure for agents: call/put walls, gamma flip, net GEX, dealer regime (CHOP/TREND/BREAKOUT), forecast band, VIX term structure, historical replay, and event webhooks. Over MCP (Streamable HTTP) or a REST v1 mirror on one key. Informational data only; not investment advice, and not the Defiance ZDTE ETF.
Scored across 13 tools
Most tools are cleanly separated by resource: credits, market data, history, and subscriptions. The only mild ambiguity is between get_market_structure and get_regime, and between get_day and get_regime_segments, but their descriptions clearly distinguish granularity and purpose.
The set overwhelmingly follows a snake_case verb_noun pattern like get_*, create_*, and list_*. It loses a point for minor deviations such as 'unsubscribe' instead of 'unsubscribe_event' and the terse 'get_day' compared to fuller names like get_market_structure.
Thirteen tools is well within the ideal range for a dedicated market-structure API. The set splits sensibly into data access, account/credit management, and subscription lifecycle tools, so each tool has a clear reason to exist.
The surface covers current market structure, current regime, historical day replays, historical regime segments, available dates, field documentation, credit management, and the full subscribe/list/unsubscribe lifecycle. No obvious dead-end operations are missing, and create_credit_checkout explicitly points to get_credit_balance for follow-up.
Create a Stripe Checkout link for the authenticated key. Does not charge or fund until payment is authorized and confirmed. Return and check get_credit_balance.
| Name | Required | Description | Default |
|---|---|---|---|
| credits | Yes | Whole number of credits to buy, within the published minimum and maximum purchase. Each credit costs credit_unit_price_cents (see get_access_options); the checkout total is credits times that price. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only indicate non-read-only and non-idempotent. The description adds the key behavioral fact that no charge or funding occurs until Stripe confirms payment, and it points to the balance check as the verification step. This materially improves the agent's understanding of side effects.
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, front-loaded with purpose. The third sentence is slightly awkward ('Return and check get_credit_balance') but still compact and 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 side-effecting checkout tool with no output schema, the description could more explicitly state what is returned (e.g., the checkout URL) and clarify the payment flow. The schema and annotations cover credits and safety, but the return contract is left implicit.
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 parameter is fully described with min/max and the price formula including get_access_options. The description adds nothing to parameter meaning, so it meets the baseline but does not exceed 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?
States a specific verb and resource: 'Create a Stripe Checkout link for the authenticated key.' This clearly identifies the operation and distinguishes it from siblings such as get_credit_balance and create_guest_key.
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 frames usage: create a checkout link for the authenticated key, expect no charge until payment is authorized and confirmed, and follow up with get_credit_balance. It does not name alternatives or explicit when-not conditions, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a zero-credit API key, returned once. Save it securely, configure HTTP Authorization: Bearer, and reconnect. Does not authenticate this connection. No arguments.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations mark this as a write operation (readOnlyHint false) and non-idempotent. The description adds that the key is returned only once, which is critical behavioral information, and clarifies it does not authenticate the current connection. This goes beyond annotations without contradicting them.
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 concise sentences: the first states the core purpose, the second provides actionable usage steps, and the third clarifies scope. No wasted words; the most important 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 tool with no parameters and no output schema, the description fully covers what an agent needs: what it creates, that the key is shown once, how to use it, and a caveat about authentication. Nothing essential 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?
The tool takes no parameters, and the schema confirms an empty object. The description states 'No arguments,' which is appropriate. With zero parameters, the baseline is 4; no further semantic detail is possible or needed.
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 creates a zero-credit API key, with specific details like 'returned once' and 'accountless'. This distinguishes it from siblings such as create_credit_checkout (which involves purchasing credits) and the read-only data tools.
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?
Provides direct instructions: save the key securely, configure HTTP Authorization Bearer, and reconnect. It explicitly notes it does not authenticate the current connection, implying it is used to establish a new authenticated session. While it doesn't name alternatives, the context is clear given the sibling list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free pricing and accountless access instructions. Start here; no website account required.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds a useful access-related detail beyond those annotations: no website account is required. It does not describe return shape, but the annotations lower that burden.
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-loads the core message in the first sentence. The second sentence adds useful 'Start here' guidance but partly repeats the earlier 'accountless' idea with 'no website account required,' so it is not completely free of redundancy.
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 informational tool, the description adequately covers what the tool is about and the access precondition. It does not specify the exact return format, and there is no output schema to compensate, but the tool's simplicity makes this 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?
The tool has zero parameters and full schema coverage, so the description does not need to document inputs. The no-parameter baseline applies, and the description's 'no website account required' note correctly implies the tool needs no account-related arguments.
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 identifies the resource as free pricing and accountless access instructions, so an agent can tell this is an informational/onboarding tool. It lacks an explicit verb such as 'returns' or 'retrieves' and does not contrast itself with sibling tools, which keeps it from a 5.
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?
'Start here' gives an explicit cue that this is the intended entry point for access/pricing/onboarding questions, and 'no website account required' sets an access condition. It does not name alternative tools or state when not to use it, so it is clear but not fully prescriptive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free balance check for the API key in this connection's HTTP header. Never pass a key as an argument.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint false, so the safety profile is covered. The description adds useful behavioral context by specifying that the API key is taken from the HTTP header and that passing a key as an argument is forbidden. 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?
Two short sentences with no filler. The core purpose is front-loaded, and the critical 'never pass a key' warning is included without bloating the description.
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 balance check, the description is complete. It explains where the API key comes from, warns against passing arguments, and the annotations cover idempotency and non-destructiveness. No output schema is present, but this requires no special return-value explanation.
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 input schema is empty, so the baseline is 4. The description reinforces that no key argument should be passed, which clarifies the intended zero-parameter usage beyond the schema itself.
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 balance check for the API key already present in the connection's HTTP header. It uses a specific verb ('balance check') and resource ('API key'), and makes the zero-argument nature explicit, distinguishing it from any key-management or purchase 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?
The description gives clear context: use this to check the balance of the connection's API key without passing credentials. It does not explicitly name alternative tools or state when not to use it, but the instruction 'Never pass a key as an argument' provides practical invocation guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Per-day SPX market-structure timeline + summary for one replay date (YYYY-MM-DD). Data only -- not investment advice or a trade recommendation.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | Replay date in YYYY-MM-DD; use list_history_dates for the set of valid dates. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the 'data only' disclaimer and the 'timeline + summary' output shape, which is useful but does not add deep behavioral detail. No contradiction with annotations exists.
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 sentence that front-loads the core purpose and then adds a concise disclaimer. Every part earns its place, and the format is easy to scan.
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 tool is simple: one required parameter, no output schema, and strong annotation coverage. The description communicates the essential return concept—timeline plus summary—for a single replay date. It could mention which sibling supplies valid dates, but the schema already handles that, so the description is nearly complete for this complexity level.
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% because the only parameter, date, is fully described with a format pattern and guidance to use list_history_dates. The description adds minimal parameter-specific meaning beyond confirming it is a single replay date. The baseline of 3 applies when the schema already documents the parameters well.
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 deliverable: a per-day SPX market-structure timeline plus summary for one replay date. It clearly identifies the resource (SPX market structure), the scope (per-day, one replay date), and sets it apart from sibling tools like list_history_dates or get_regime.
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 no explicit guidance on when to choose this tool over siblings. It notes that it is data-only and not advice, but does not say when to use get_day versus get_market_structure, get_regime, or other related tools. The parameter schema mentions using list_history_dates for valid dates, but this is not surfaced in the description itself.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Static, versioned dictionary of every field this surface emits: unit, value set where the producer has one, and a one-sentence meaning, plus the shared response conventions (tier, delay, timestamps, and how missing data is reported). No inputs; call once per session.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context beyond the annotations: it is static and versioned, takes no inputs, and should be called once per session. The annotations already cover read-only and idempotent behavior, so the description's snapshot semantics and call cadence are valuable additions without redundancy.
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 with the core purpose front-loaded and the usage directive stated crisply. There is no wasted wording, and no information is repeated from the annotations.
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-input reference tool, the description is complete: it defines what the response covers, the call cadence, and the no-input contract. Since there is no output schema, describing the response contents in prose was necessary and sufficient.
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 and an empty input schema. The description explicitly states 'No inputs,' which removes any ambiguity and earns the baseline credit for a zero-parameter tool.
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 this is a static, versioned dictionary of every field the surface emits, including units, value sets, meanings, and shared response conventions. This clearly identifies the resource and purpose, and distinguishes it from data-query siblings like get_day or get_regime by being a metadata reference tool.
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 clear usage context: it is a no-input reference to call once per session, so an agent knows when to invoke it and that the result can be reused. It does not explicitly name alternatives or state when not to use it, but the distinction from the data-query siblings is clearly implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Current computed SPX dealer market structure (walls, gamma flip, net GEX, regime), recomputed ~every 10s during market hours: scored pressure-point strike ladder, implied 50%/80% forecast-band ranges, strike activity (volume/OI), and VIX term-structure context. Also the 0DTE ATM-straddle expected move and its session fence, max pain, the running session open/high/low with the prior close and gap, order-flow measurements, a top-10 net-GEX strike profile, and chain vanna/charm totals with a top-10 strike ladder. Realtime requires a funded X-API-Key (create one at https://zdte.ai/agent/credits); without a key this serves a delayed headline preview only (regime, spot, walls, gamma flip, net GEX). Data only -- not investment advice or a trade recommendation.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond that: recomputation cadence (~every 10s during market hours), the realtime-vs-delayed data split, and the 'Data only -- not investment advice' disclaimer. It does not fully detail the output shape, but with no output schema and a rich payload, the description carries a heavy burden and mostly meets it.
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 dense block that front-loads the core resource and then lists many components. It is information-dense but somewhat run-on, with a long comma-separated enumeration that could be structured into clearer sentences or bullets. Every sentence earns its place, but the wall-of-text format reduces scannability 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?
For a zero-parameter, read-only data tool with no output schema, the description is quite complete: it names the data categories, the refresh cadence, the auth requirement, the degraded mode without a key, and the non-advice disclaimer. The main gap is that it does not specify the exact response format or field names, but the description's enumeration largely compensates for the missing output schema.
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 there is no parameter semantics burden on the description. The schema already documents an empty object with additionalProperties=false. The description's detailed enumeration of what the response contains compensates for the lack of an output schema, effectively telling the agent what data it will receive without needing 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 opens with a specific verb ('get') and a precise resource ('current computed SPX dealer market structure'), then enumerates the concrete components (walls, gamma flip, net GEX, regime, strike ladder, forecast bands, etc.). It clearly distinguishes itself from siblings like get_regime and get_day by naming the full market-structure payload rather than a single regime or day snapshot.
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 states when realtime data is available (requires a funded X-API-Key) and what happens without a key (delayed headline preview only). It also names the exact place to create a key. This gives an agent clear go/no-go conditions and distinguishes the realtime vs preview behavior, which is more actionable than most sibling-routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Current SPX dealer regime label + confidence only. Realtime with an X-API-Key; without a key this serves a delayed preview.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering safety. The description adds meaningful behavioral context: it discloses the realtime vs delayed preview distinction and the API key requirement, which are not in annotations. It also clarifies the response is limited to label and confidence, setting expectations about data scope.
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 with no fluff. The core purpose is front-loaded, and the authentication caveat is a single additional clause. Every word 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 simple zero-parameter read-only tool, the description covers the essential: what it returns, the realtime condition, and the auth requirement. It lacks an explicit description of the output format (e.g., does 'confidence' mean a number 0-100 or a string?), but since there is no output schema, the description could be slightly more explicit. However, given the simplicity and the annotations covering safety, it is adequately complete.
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 schema is trivially complete. Baseline for no parameters is 4. The description does not need to explain parameters since there are none. It adds no param info but none is 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 states a specific resource (SPX dealer regime), the exact data returned (label + confidence), and the scoping qualifier 'current' and 'only'. This clearly distinguishes it from sibling tools like get_regime_segments, which likely returns more detailed regime data, and get_market_structure, which covers a different concept.
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 explains the realtime vs delayed preview behavior based on API key presence, which is context about authentication and freshness. However, it does not explicitly guide the agent on when to choose this tool over alternatives like get_regime_segments or get_market_structure. The 'label + confidence only' hint implies it is for a quick summary, but no direct comparison or exclusion is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compressed dealer-regime segment tape for one replay date (YYYY-MM-DD).
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | Replay date in YYYY-MM-DD; use list_history_dates for the set of valid dates. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds the 'compressed' nature and single-date scope, but it does not disclose what the tape contains, whether decompression is needed, or any response-size or pagination 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 one short, front-loaded sentence with no filler. 'Compressed' and the date-format parenthetical each add useful context, and nothing included 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 a simple single-parameter, read-only, idempotent tool with rich annotations and full schema coverage, the description is close to sufficient. However, there is no output schema and no explanation of what a 'regime segment tape' actually contains, so the agent still has limited ability to predict the return value.
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, date, is fully documented in the schema with a pattern, format description, and pointer to list_history_dates. The description adds only the phrase 'one replay date (YYYY-MM-DD)', which is redundant with the schema, so a baseline score of 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 identifies a specific resource—a compressed dealer-regime segment tape—and scopes it to one replay date. It is not a tautology of the name/title and is distinguishable from siblings like get_regime and get_day, though it lacks an explicit verb like 'returns' or 'retrieves.'
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 implies the tool is used to get a date-specific regime segment tape, and the schema points to list_history_dates for valid date values. However, it does not explicitly compare this tool to siblings such as get_regime or get_market_structure, nor does it say when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free catalog of available historical SPX market-structure replay dates. No API key required; actual replay datasets are paid.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds meaningful context beyond annotations: the catalog is free, requires no API key, and only the actual replay datasets are paid. 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?
Two terse sentences deliver the core function first and then add the access/cost caveat. No redundant words 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?
For a zero-parameter, read-only catalog operation, the description provides all necessary context: what is listed (dates), the domain (SPX market structure), and the free-vs-paid boundary. An output schema is absent, but the simple list nature makes the response type reasonably predictable.
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 input parameters, so the schema fully covers invocation. The description's mention of 'no API key required' is access context rather than parameter semantics. Baseline 4 applies because there are no parameters to document.
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 purpose: providing a free catalog of available historical SPX market-structure replay dates. It clearly distinguishes the date catalog from the actual replay datasets and the resource/scope is unambiguous. The verb is implied by 'catalog' but the operation is clear.
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 explains when this tool is appropriate: discovering available dates without an API key, while the underlying datasets are paid. It does not explicitly name a sibling alternative, but no other sibling appears to perform the same date-list function.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List this agent's active event subscriptions.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds useful scoping context ('this agent's active') that is not present in the annotations, clarifying that it returns a filtered subset rather than all possible subscription records.
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, front-loaded sentence with no filler or redundant restatement. It conveys the action, the resource, and the scope in nine 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 parameterless, read-only list operation, the description plus annotations fully equip an agent to select and invoke the tool. No return schema is provided, but the word 'List' sufficiently implies the output is the set of active subscriptions.
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?
With zero parameters and 100% schema description coverage, there is nothing for the description to add about arguments. The baseline of 4 for parameterless tools 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 uses the specific verb 'List' with an explicit resource ('this agent's active event subscriptions'), making the tool's purpose unambiguous. It is clearly distinct from sibling tools like subscribe_event and unsubscribe, which perform mutations, and from data-retrieval tools like get_regime.
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 phrase 'this agent's active event subscriptions' clearly communicates the query scope and implies this is the tool to call when an agent needs to see its existing subscriptions. It does not explicitly name alternatives or exclusions, but no direct alternative for simply listing subscriptions exists among the siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Subscribe a callback URL to a market-structure event (zero_gamma_flip | new_wall | regime_transition).
| Name | Required | Description | Default |
|---|---|---|---|
| event | Yes | Which market-structure event to subscribe to: zero_gamma_flip, new_wall, or regime_transition. | |
| callback_url | Yes | HTTPS URL that receives a POST when the event fires. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate this is not read-only and not idempotent, so the mutation aspect is covered. The description adds that a callback URL receives POST notifications, but it does not disclose whether subscribing twice creates duplicates, overwrites, or errors, nor does it mention that subscriptions persist until explicitly removed.
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, focused sentence that states the action, the target, and the allowed values with no filler. The event enum is compactly listed and 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 two-parameter tool with fully documented schema and adequate annotations, the description is mostly complete. The only meaningful gap is the lack of explicit side-effect or management context (e.g., 'manages subscription lifecycle via list_subscriptions/unsubscribe'), but this is not necessary to make a correct call.
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%: both event and callback_url have meaningful descriptions, and event has an enum. The description repeats the enum values but adds no new semantic detail beyond the schema, 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 uses a specific verb ('Subscribe') with a clear resource ('callback URL') and enumerates the exact event types (zero_gamma_flip | new_wall | regime_transition). It clearly distinguishes the tool from siblings like unsubscribe and list_subscriptions by using the opposite action for the same domain.
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 implies when to use the tool: when the agent needs to register a callback for a market-structure event. However, it does not explicitly mention alternatives or exclusions, such as 'use list_subscriptions to view existing subscriptions' or 'use unsubscribe to remove one.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Remove an event subscription by id.
| Name | Required | Description | Default |
|---|---|---|---|
| subscription_id | Yes | The subscription id returned by subscribe_event. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already signal that this is destructive (destructiveHint=true), not read-only (readOnlyHint=false), and idempotent (idempotentHint=true). The description adds that the operation removes an event subscription but does not provide additional behavioral context such as permissions, side effects, or failure 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 efficient sentence with no filler. It states the action, target, and parameter requirement in minimal 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?
This is a simple one-parameter tool with rich annotations covering destructive and idempotent behavior, so the description is largely sufficient. It does not mention return values or consequences, but the low complexity and annotation coverage keep this from being a significant 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%, and the schema explicitly defines subscription_id as 'The subscription id returned by subscribe_event.' The description adds only 'by id,' which does not materially enhance the schema's already clear parameter semantics.
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 ('Remove'), a clear resource ('event subscription'), and a precise mechanism ('by id'). This clearly distinguishes it from sibling tools like subscribe_event and list_subscriptions.
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 inverse relationship with subscribe_event, and the schema notes the subscription id comes from subscribe_event. However, the description itself does not explicitly state when to use this tool, when not to, or mention list_subscriptions as a way to retrieve existing subscription ids.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
create_credit_checkoutcreate_guest_keyget_access_optionsget_credit_balanceget_dayget_field_guideget_market_structureget_regimeget_regime_segmentslist_history_dateslist_subscriptionssubscribe_eventunsubscribe
Add one secure layer between your agents and this server.