zdte.ai SPX Market Structure

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, so the mutation and safety profile are covered. The description adds genuinely useful non-annotation context: the deferred-effect semantics ('Does not charge or fund anything until payment is authorized and confirmed'). It does not cover link expiry, single-use, or reuse behavior, which keeps it from a 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 tight sentences with no filler; the core action is front-loaded and the deferred-charge caveat follows immediately. 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?

No output schema exists, but the description implies the return is a payment link a person opens, which is adequate for a single-parameter tool whose fee semantics are already stated. Link lifecycle details (expiry, single-use) would be the remaining 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?

There is only one parameter and schema description coverage is 100% — the schema already explains the unit, min/max, and pricing math. The description adds no parameter-level detail beyond what the schema provides, so the baseline 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?

States a specific verb and resource ('Create a payment link that adds prepaid credits') and describes the mechanism — a person opens the link to pay. An agent can distinguish this from siblings like subscribe_event or get_credit_balance without opening the 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?

The description implies its use case (buying prepaid credits via a shareable link) but never states when to prefer it over alternatives such as subscribing via subscribe_event or checking balance first. Usage is inferable but not explicit, and there are no exclusions.

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 non-read-only, non-idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds high-value traits beyond that: the key is shown exactly once, connection_authenticated signals this session is already authenticated, and other connections must send an 'Authorization: Bearer' header.

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 sentences, all substantive: what it creates, how the result is consumed, and the no-key alternative path. Front-loaded with the creation fact, though the final sentence about Connect prompts is dense and slightly harder to parse.

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 carries the burden of explaining the response, and it does: the one-time key reveal plus the connection_authenticated field. An agent has everything needed to call this and interpret the result.

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?

Zero parameters, so the baseline is 4. The description confirms 'No arguments,' which matches the empty schema with additionalProperties: false, leaving no ambiguity for the caller.

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?

Names a specific verb and resource ('Creates a zero-credit API key') and specifies the key's nature, which distinguishes it from the billing-oriented sibling create_credit_checkout. It stops short of explicitly naming that sibling, so an agent must infer the boundary from context.

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?

States upfront that no arguments are needed, and explicitly flags the case where the tool is NOT required: OAuth-capable clients get an automatic Connect prompt for paid/account tools, 'so no key is required.' That is a genuine when-not condition, though it is framed as a caveat rather than a decision rule.

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, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds useful context that the caller needs no website account and that the payload concerns pricing plus onboarding steps, but says nothing about rate limits, freshness of prices, or response shape.

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?

A single compact sentence with no filler and no repetition of the title. The lead-in 'Free:' is slightly opaque but the sentence is front-loaded and efficient.

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 input parameters and no output schema, the description carries the burden of telling the agent what comes back, and it only gestures at 'current prices and the accountless access steps.' It is adequate to identify the tool's subject but thin on how complete or current the returned access options are.

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 zero parameters, so there is nothing for the description to disambiguate; per the baseline for param-less tools this scores high by default.

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 names the content returned (current prices and the accountless access steps) but never states a clean verb+resource, opening instead with the fragment 'Free:'. It gives a partial sense of what the tool is but does not clearly distinguish it from siblings like create_guest_key or list_subscriptions, which also touch access/account concepts.

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?

There is no explicit when-to-use statement and no named alternative. The clause 'no website account required' hints at a precondition but does not tell the agent when to call this versus create_guest_key or create_credit_checkout, so routing must be inferred.

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 safety is covered. The description adds genuinely new context: the credential source is the connection's HTTP header rather than a parameter, and the call is free. It still doesn't describe what a balance value looks like or any rate limits, keeping it out of 5 territory.

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?

A single sentence that front-loads the operation and the credential source, with no redundant restatement of the title or name.

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 no-parameter, read-only tool with full schema coverage and no output schema, the description covers the essentials: what it returns (a balance), how it authenticates, and that it is free. It could say more about the relationship to create_credit_checkout, but no critical calling information 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?

Zero parameters means the schema has nothing to explain, and the description correctly notes that no key argument is accepted, preempting an agent from trying to pass one. That is the only meaningful semantic point for this 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 names a specific operation (balance check) and the exact resource it reads (the API key in this connection's HTTP header), which is more precise than the title alone. It does not explicitly distinguish itself from siblings like create_credit_checkout, so it stops short of 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?

Mentioning that the check is 'free' implies it is a safe, low-cost call, and 'takes no key argument' clarifies the invocation contract. However, it never states when to prefer this over create_credit_checkout or what to do when the balance is low, so usage guidance is only implied.

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, openWorld and non-destructive, so the safety profile is covered. The description adds real value beyond that by disclosing the shape of the returned content and the one-date-per-call constraint, though it says nothing about response size, pagination, or latency for a day-scale timeline.

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 front-loaded sentences that lead with what is returned, then the input constraint, then the disclaimer. Dense but every sentence carries a distinct piece of information; no filler beyond the standard disclaimer.

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 present, the description carries the burden of describing the return surface, and it does so by listing the intraday timeline components plus the day summary. Combined with the fully documented single parameter and the annotation coverage, an agent has enough to invoke and interpret it, with only pagination/size undisclosed.

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 date parameter already documents the YYYY-MM-DD pattern and the catalog constraint. The description only repeats the format and the per-call cardinality, adding no syntax or validation detail beyond the schema, which is the expected baseline for full coverage.

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+resource: the full market-structure history of one past trading day, and enumerates the payload contents (walls, gamma flip, net GEX, regime, spot, day summary). It does not name or explicitly differentiate itself from siblings like get_market_structure or get_regime_segments, so an agent must infer that this is the historical per-day variant.

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?

"One replay date (YYYY-MM-DD) per call" conveys the cardinality and the required identifier, and the date must come from the replay date catalog. However, there is no explicit when-to-use versus when-not-to-use, and no pointer to list_history_dates or get_market_structure as the alternative for live/other views.

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, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: it is static and versioned, so results are stable and cacheable, and it discloses that conventions for tiers, delays, timestamps, and missing-data reporting are documented inside.

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 dense sentences, front-loaded with what the guide contains and closed with the operational facts (no inputs, static per version). Every clause carries information; there is no 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?

With no output schema, the description must convey the return content, and it does so by listing the categories (unit, value set, meaning, shared response conventions). It stops short of describing the guide's organization/lookup structure, which would fully close the loop for a reference 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?

There are zero parameters, so the baseline is 4. The description correctly confirms this by stating 'No inputs', leaving no ambiguity about whether arguments should be supplied.

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 names a specific resource (a static, versioned field dictionary for this surface) and enumerates exactly what it contains: units, value sets, one-sentence meanings, and shared response conventions. It also states that it takes no inputs and is static per version, which makes it immediately distinguishable from the data-fetching 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?

Usage is only implied: an agent can infer this is the lookup table for interpreting fields emitted by the sibling tools, but the description never says when to consult it (e.g. before parsing other tool output) or when it is unnecessary. No alternative or exclusion is named.

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 read-only, idempotent, open-world, non-destructive. The description adds real behavioral context beyond them: ~10s recompute cadence during market hours, the funded-API-key requirement, and a degraded fallback (delayed headline preview with regime/spot/walls/gamma flip/net GEX only) when unauthenticated.

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 key value proposition, but the first two sentences restate the same field list ('walls, gamma flip, net GEX, regime') redundantly, and the long enumeration of outputs is not tightly organized. It is informative but bloated.

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 carries the burden of describing returns, and it does so thoroughly: pressure-point strike ladder, 50%/80% bands, VIX term structure, 0DTE straddle move, max pain, session OHLC/gap, order flow, top-10 GEX profile, vanna/charm totals. The auth/fallback story and the 'not investment advice' disclaimer round it out.

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 zero parameters, so there are no argument semantics to document; baseline is 4. Nothing in the description misleads about inputs.

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 resource (SPX dealer market structure) and positions it as the fullest realtime read, enumerating walls, gamma flip, net GEX, regime and strike-level detail. It reads as a superset of the sibling get_regime, but that differentiation is implied rather than stated.

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 largest realtime read' and the note that a funded key is needed for the full structure suggest when to pick this over a lighter sibling like get_regime, but no explicit when/when-not or alternative-naming guidance is given.

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 cover read-only, idempotent and non-destructive. The description adds behavioral context those annotations cannot express: realtime data with an API key versus a delayed preview without one, which is an authentication and freshness constraint the agent needs. Rate limits and the exact preview delay are unstated, so not a 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 clauses separated by a semicolon, with the return scope front-loaded and the auth/freshness caveat second. Every sentence earns its place and nothing is repeated from the structured fields.

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 parameters and no output schema, the description carries the whole burden, and it does say what comes back (label plus confidence) and how access affects freshness. The output's shape or possible label values are not described, which is a minor residual gap for a tool whose entire value is the returned label.

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 zero parameters, so per the rubric the baseline is 4. There is nothing for the description to disambiguate, and it correctly adds no parameter noise.

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 names a specific resource and scope: the *current* SPX dealer regime label plus its confidence, and explicitly rules out walls, gamma flip, net GEX and strike detail. That exclusion set distinguishes it from data-heavy siblings like get_market_structure and from the segment-oriented get_regime_segments without the agent opening any 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?

It supplies a clear use case - 'a small read for checking whether conditions have changed' - and the exclusions imply when not to use it. It stops short of naming an alternative tool by name for the fuller picture, so it lands just below the top band.

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 the description adds genuinely useful scope disclosure: the exclusions (no walls, gamma flip, net GEX, spot) tell the agent this is a narrow content window rather than a full snapshot. It does not mention pagination or response ordering, but the content-boundary disclosure is the valuable part.

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?

Dense and front-loaded: the scope is stated first, exclusions second, and the parameter constraint last. It is written as a verbless fragment, which is slightly awkward, but every clause carries information.

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 steps in to say the return is a list of regime segments with start and end times, which is what an agent needs to consume the result. Nothing important is missing for a simple one-parameter read 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?

Schema coverage is 100% and the schema already gives the pattern and the 'replay date catalog' constraint, so the baseline is 3. The description only restates the YYYY-MM-DD format and adds that it is one date per call, which is largely implied by the single-property 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?

States a specific resource (regime segments for one past trading day) and explicitly scopes it against richer siblings by ruling out walls, gamma flip, net GEX and spot. An agent can distinguish this from get_regime or get_market_structure without opening any 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?

Frames the call as the 'compact replay' for when only the regime change tape is wanted, and states the one-date-per-call constraint. It never names the alternative tool (e.g. get_regime) that would be used when the excluded fields are needed, so selection is implied rather than explicit.

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, 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.

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.

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.

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds nothing behavioral beyond that — no statement about what happens to a missing/already-removed id (relevant given idempotentHint), no auth requirements, and no effect on the underlying event.

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 sentence, front-loaded with the action and resource, and the qualification about the id source is placed where it matters. Slightly redundant with the schema's own description of the same parameter.

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 removal tool whose annotations already state idempotency and non-destructiveness, the description is sufficient. A note on behavior for an unknown or already-removed id would close the remaining 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 description's parameter explanation duplicates the schema text almost verbatim, adding no format or constraints. Baseline 3 applies when the schema carries the parameter documentation.

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 (Remove) and resource (an event subscription), scoped by the identifier used to target it. The sibling pair subscribe_event/unsubscribe_event is distinguishable by name, though the description itself does not explicitly contrast the two.

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 naming the required subscription_id and noting where it comes from (the create call), but there is no explicit when-to-use guidance and no mention of list_subscriptions as the way to discover an id.

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