0DTE Confluence

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: the gate criteria, the inclusion of a 'fade fragility veto', and three explicit non-checks that bound its verdict. It stops short of stating whether the check is purely local or triggers a fetch by default, and does not describe the pass/fail signal itself.

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

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

Four tight sentences that lead with the gate definition and end with the second parameter's use. Dense domain jargon ('A+/B', '6/8', 'fade fragility') is efficient for its audience, though it packs several criteria into one sentence.

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?

An output schema exists, so return values need not be explained, and the behavioral scope is well bounded. However, with two parameters at 0% schema coverage and an unexplained relationship between alert_json and use_latest, plus undefined threshold semantics ('6/8'), the definition leaves gaps an agent must guess at.

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 0%, so the description must compensate. It explains alert_json's role ('check that specific record without fetching another alert'), which also implies the default latest-alert fetch behavior, but use_latest is never mentioned and the default '' / true interaction is left ambiguous.

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 concrete evaluation task (a 'pro planning gate') and enumerates the exact criteria applied — valid A+/B record, score >= 6/8, 9:45–force-flat window, level and direction sanity — so the agent knows this validates an alert rather than fetching one. It does not, however, contrast itself with siblings like get_latest_alert or list_alert_history, leaving the boundary implied.

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 'Pass alert_json to check that specific record without fetching another alert', which tells the agent how to target a specific record. The negative list ('Does not check subsequent stop-outs, live structure, or broker positions') scopes limitations but is not framed as when-not-to-use or as an alternative tool, so the agent must infer the correct invocation context.

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 must disclose behavior, but it only mentions jargon like 'fill E' and 'fallback only' without explaining what the tool does, what side effects it has, or what it returns. This is a significant gap for a tool that likely performs computation or formatting.

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 extremely short, which could be seen as concise, but it lacks structure and clarity. It is cryptic and under-specified, offering no front-loaded purpose or actionable steps. It is not a case of effective conciseness but rather inadequate specification.

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 complex (involves bracket plan generation, scale-in logic, structural rail stops) yet the description omits essential details like how the fallback works, what the output structure is, and how it relates to entry_premium. Even with an output schema, the description does not help an agent understand when or how to invoke the tool 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 description coverage is 0%, and the description does not explain any of the four parameters (broker, alert_json, use_latest, entry_premium). The reference to 'fill E' does not map to any parameter. The description provides zero value for parameter understanding.

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 does not clearly state that the tool formats a bracket plan. It reads like a trading strategy note (scale-in, structural rail stop, fallback) rather than a verb+resource statement. The name 'format_bracket_plan' suggests a formatting function, but the description never says that, leaving the purpose ambiguous.

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 mention of when to use this tool versus its siblings (e.g., plan_entry, plan_alpaca_entry). The description gives no context, conditions, or alternatives, so an agent has no guidance on selecting it.

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 the calculation window (rolling 5-min) and asset set, and clarifies it is not a trigger. However, it does not mention what the output represents, how many data points are included, or any limitations; some of this is likely covered by the output schema.

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 two short sentences with no filler. The core metric and asset list are front-loaded, and the usage caveat is immediate and memorable.

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 tool with an output schema present, the description provides sufficient context: the metric, the assets, and the intended role. It could add a bit more about how to interpret the correlation grid or when to favor it over sibling correlation tools, but the essentials are covered.

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. The baseline of 4 applies, and the description adds useful context about the assets and rolling return methodology even though no parameters need explanation.

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 a specific metric (rolling 5-min return correlation) and the exact resources (SPY/QQQ/IWM/DIA). It also positions the tool as a portfolio overlay rather than a signal trigger, which separates it from alert-style siblings, though it does not name a specific 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?

"Portfolio overlay, not a trigger" gives clear guidance on when to use it: as background context for portfolio assessment, not as an entry/exit trigger. It provides a useful exclusion but stops short of naming alternatives or explicit when-to-use conditions.

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 behavioral burden. It adds one genuine behavioral trait ('not a trigger') and frames the tool as a context read, but it omits data source, refresh cadence, or interpretation details. 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?

The description is appropriately short and front-loads the asset list before the usage caveat. However, 'UW' is unexplained shorthand, pushing it slightly from concise toward under-specified.

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 empty parameter list and presence of an output schema lower the burden, and the not-a-trigger caveat is essential. Still, the cryptic 'UW' and lack of any relationship to related risk tools leaves an agent without full confidence in sibling selection.

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 schema coverage is 100%, so there is no parameter meaning for the description to add. The baseline of 4 applies because no parameter documentation gap exists.

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 concrete assets (VIX, TNX, UUP) and assigns a purpose ('risk-tone overlay'), so an agent can roughly tell what it does. However, it lacks a clear verb—'UW' is cryptic—and it does not sharply distinguish this from overlapping risk/sentiment siblings such as get_fear_greed or get_index_health.

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 'risk-tone overlay — not a trigger' phrase gives an implied usage context and an explicit exclusion, which is more than no guidance. But it never names alternative tools or states when an agent should prefer this over other risk-related getters.

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

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

No annotations are provided, so the description carries the full behavioral disclosure burden. It does disclose that the tool provides real-time data, uses Lee-Ready logic, and supports 1m/5m intervals, but it leaves unclear what 'Pro tier' implies and whether the result is a snapshot or a series.

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 compact and front-loaded with the core method and metric. The 'Pro tier. interval: 1m | 5m' portion is terse and slightly awkward, but there is no redundant 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?

Given an output schema exists and the tool has only two simple parameters, the description is reasonably complete for basic invocation. However, it fails to mention the instrument parameter, potential default behavior, or how this tool fits among related liquidity and order-flow tools.

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 0%, so the description must compensate. It documents the allowed interval values ('1m' | '5m') but completely omits the instrument parameter, which is a significant gap given the schema provides no descriptions either.

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 operation: it aggregates Net CVD using Lee-Ready on minute bars, which is a specific and distinctive computation. It does not explicitly contrast itself with sibling tools like get_order_flow or get_liquidity_concentration, but the unique CVD focus makes the purpose recognizable.

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 does not say when to use this tool versus alternatives such as get_order_flow or get_liquidity_concentration. It only notes 'Pro tier' as a possible access constraint, which is not usage guidance.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not state whether this is a read-only retrieval, how the 'board' is structured, whether access or subscription constraints apply, or what operational behavior the agent should expect despite the 'Bundle tier' fragment.

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 appropriately short and front-loads the core contents. The trailing 'Bundle tier.' is cryptic and adds little operational value, but it does not bloat the overall 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?

With no annotations, no parameter guidance, and no usage context relative to similar get_* tools, the description is not sufficient for an agent to confidently select this tool over get_swing_structure or get_market_clock. The output schema helps with return value shape, but the intended context and access implications are left unclear.

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 0%, and the description never mentions the symbol parameter or its SPY default. The agent must rely entirely on the property name and default, while the description adds no semantic value to parameter understanding.

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 resource as a 'Daily Structure Board' and enumerates concrete contents: automated pivots, ATR targets, and overnight boundaries. This goes beyond a tautology and gives the agent a clear sense of what the tool provides, though it does not explicitly distinguish it from sibling tools like get_swing_structure.

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 word 'Daily' and the listed contents imply the tool is relevant when an agent needs daily pivot, ATR, or overnight-boundary context. However, there is no explicit when-to-use guidance, no exclusions, and no mention of alternative tools, so usage must be inferred rather than stated.

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 burden; it usefully discloses that the output is a 1σ band computed from ATM IV for only the remaining session. It does not describe the exact output shape or edge cases, but as a read-only getter it does not hide destructive or mutating 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 tight, front-loaded phrase with no filler; every word ('1σ', 'ATM IV', 'remaining session') contributes distinct 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?

Because an output schema exists, the return shape does not need explanation, and the tool is simple with a single optional parameter. However, the missing usage guidance and implicit parameter linkage leave the definition only minimally 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?

Schema description coverage is 0% and the description does not mention the symbol parameter or explicitly connect it to the underlying used for the expected-move calculation. The parameter name and default 'SPY' make it self-explanatory enough to avoid a 1, but the description adds no parameter meaning.

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 resource ('expected-move band') and specifies its derivation ('from ATM IV') and horizon ('remaining session'), so an agent can distinguish it from sibling market-data tools like get_skew or get_pin. It lacks a verb, but the get_em tool name and the noun phrase make the action unambiguous.

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 'remaining session' qualifier implies the intended use case, but the description gives no explicit when-to-use or when-not-to-use guidance and names no alternatives. An agent must infer context from the sibling list rather than being told.

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 behavioral disclosure burden. It adds useful context by naming the inputs (Tape + VIX) and specifying the intraday timeframe, but it does not explicitly state that the call is read-only, how often it updates, or what output scale to expect, though an output schema is present.

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 line that front-loads the core meaning and then adds a concise usage hint. There is no filler or repetition, and every word earns its place even though 'rail' is domain-specific jargon.

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 the tool has zero parameters and an output schema, the description provides enough context about the metric and its intraday nature to allow invocation. It could be more complete by explaining when to prefer this over related sentiment tools, but that is a usage- guidance gap rather than a critical disclosure 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 input schema is empty with 100% schema description coverage, so there are no parameters for the description to clarify. The baseline of 4 applies because nothing additional is 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 that the tool returns an intraday fear/greed composite composed of Tape and VIX, which identifies the resource and scope. It does not explicitly name a sibling alternative, but the metric name and qualifiers are specific enough to distinguish it from most sibling tools like get_skew or get_correlation_grid.

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 'Intraday fear/greed composite' implies use when an intraday sentiment reading is needed, and 'Fade extremes at a rail' hints at a mean-reversion trading context. However, there is no explicit guidance on when to use this tool versus the many sibling tools, nor any exclusions or conditions.

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, but it only states what the output is about. It does not mention read-only nature, default symbol behavior, how 'near spot' is defined, or what happens when data is unavailable—though the output schema does cover return shape, the description adds no behavioral context.

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 extremely concise and front-loaded, with no wasted words. However, it is arguably too terse: it is only a noun phrase, not a full sentence, and omits information that would help an agent use the tool correctly. It earns its keep as a summary but not as a complete instructional 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?

The existence of an output schema covers return-value structure, and the single optional symbol parameter lowers complexity. But the description leaves key contextual gaps: what 'near spot' means, how the symbol parameter interacts with the profile, and when this tool should be preferred over siblings. For a tool with no annotations and no parameter descriptions, this is insufficiently 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 schema has one parameter, 'symbol', with no description, and schema description coverage is 0%. The tool description does not mention the symbol parameter, its default value, or how it affects the returned profile. The meaning of the parameter is entirely left to inference from the tool name and default value.

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 'Per-strike GEX profile near spot' identifies a specific resource (a GEX profile) and implicitly the action (retrieve/get), and the GEX-specific wording helps distinguish it from the many other get_* siblings. However, it lacks an explicit verb and does not clarify what 'near spot' precisely means, leaving minor ambiguity.

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 guidance on when to use this tool versus the many sibling tools such as get_skew or get_path_risk_score. There is no mention of use cases, exclusions, or alternatives. It is not misleading, but it offers no usage direction.

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 of behavioral disclosure, but it only states the data source and scope. It does not explain how the optional date behaves when omitted, how limit and min_score affect results, whether events are sorted, or any pagination behavior. The phrase 'graded events' hints at scoring, but that is not enough for a tool with no annotation safety or behavior hints.

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 repetition. It packs the key scope ('multi-day', 'historical', 'scanner log') into a compact phrase. However, it is thin enough that it misses important semantic detail, so it earns a strong but not perfect conciseness score.

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 three optional parameters, no annotations, low schema coverage, and many sibling tools, this description is not complete enough for an agent to invoke the tool confidently. The output schema may document return shape, but the description still fails to clarify parameter semantics, default behavior for date, or when to choose this over get_replay_today. The core selection and invocation context 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?

Schema description coverage is 0%, so the description must compensate for explaining all parameters. It only covers 'date' with 'optional YYYY-MM-DD', and does not explain 'limit' or 'min_score' at all. The one parameter it does mention adds some meaning, but the other two are left completely undocumented.

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 'multi-day historical graded events from scanner log' and indicates an optional date parameter. It lacks an explicit action verb like 'retrieve' or 'list', but the tool name plus the resource scope make the purpose reasonably clear. The 'multi-day' qualifier also helps distinguish it from get_replay_today.

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?

No guidance is provided about when to use this tool versus alternatives such as get_replay_today or list_alert_history. The phrase 'multi-day historical' implies past-date usage, but it never explicitly says 'use this for historical replays' or 'use get_replay_today for the current day's replay'. The agent is left to infer the selection criteria.

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

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It mentions the computed signals and index choices, but it does not clarify whether the tool is read-only, what time window or data source is used, or what 'health' means operationally beyond the two metrics.

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 core content is short and front-loaded, but the fragment 'Bundle tier.' adds no actionable information, and the parameter hint is formatted as a terse inline leftover. It is compact but not every part 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?

Given low complexity, a single optional parameter, and an output schema, the description is minimally viable: it states the subject matter and the parameter choices. However, it lacks any broader context for when to use the tool, and the cryptic 'Bundle tier.' line slightly undermines clarity.

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 0%, but the description partially compensates by specifying the allowed values: index: 'SPY' | 'QQQ'. It does not explain that these are tickers or how the value affects the result, but the parameter name and default make the meaning reasonably self-evident.

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 the resource as an 'Index Health Dashboard' and the substance as 'relative volume & momentum for top components,' which goes beyond a simple restatement of the name. It does not use an explicit verb like 'retrieve' or 'show,' but the intent is clear and distinguishable from the sibling market 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?

There is no guidance about when to use this tool, what question it answers, or which sibling tool might be a better alternative. The only practical hint is the allowed index values, so an agent must infer the appropriate context on its own.

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, and it does disclose genuinely non-obvious semantics: trapdoor is a stored alert-time score rather than a live rescore, eligible is a saved window flag, and _pro_eligible/_pro_reason are evaluated against today's rules rather than stop history. It still omits operational traits such as empty-result behavior or any auth/permission notes, but the semantic caveats are valuable.

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 purpose is front-loaded in the first clause, followed by field caveats and then the routing instruction; every sentence adds distinct information. It is somewhat dense with underscored field names, but nothing is padding.

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?

An output schema exists, so return values need not be explained, yet the description goes further and clarifies the trickiest stored-vs-live distinctions. For a zero-parameter read tool this is close to complete; only the empty/no-alert case and any staleness horizon are unstated.

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 the baseline is 4 and there is nothing for the description to compensate for. The field-level explanations it does provide (trapdoor, eligible, _pro_eligible/_pro_reason) add meaning beyond an empty argument 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 identifies the resource precisely as the 'Latest Discord-filtered A+/B card', which tells an agent this returns the most recent qualifying alert rather than history or a recomputed score. It is terse and leans on domain jargon ('A+/B card'), but the scope and freshness distinction from siblings like list_alert_history is inferable.

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 gives an explicit forward-routing instruction: 'Use check_alert_tradeable before planning', which is a concrete when-to-go-next rule. It stops short of naming when this tool should not be used (e.g. wanting history vs. latest), so it is clear context without explicit 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?

With no annotations, the description carries the burden. It discloses that the tool is advisory, has liquidity gates, and does not auto-execute — useful behavioral context — but it does not explicitly state read-only status, data freshness, or response behavior beyond the existing output schema.

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 deliver the key point and the most important caveat with no filler. The advisory stance is front-loaded and the anti-execution warning is immediately actionable.

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 tool with an output schema, the description covers the essential context: purpose, timeframe, single-name scope, liquidity gating, and non-execution. The only minor gap is that 'liquidity gates' is not expanded, but the output schema can carry that detail.

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 the schema is fully covered, so the description has no parameter burden. The baseline of 4 applies because no parameter explanation is 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 identifies a specific resource — a single-name 0DTE Friday board — and its advisory nature. It is clear enough to distinguish from execution-oriented siblings like plan_robinhood_entry, though it does not explicitly contrast with related get_* board 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?

It conveys when to use it (Friday, single-name 0DTE context) and explicitly warns it is not auto-exec, which tells the agent not to route it to execution. However, it does not name alternative tools or exclusion conditions relative to 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?

No annotations are provided, so the description must carry the behavioral burden. It communicates that the tool returns macro-economic events with volatility forecasts and implies an overview-style read-only panel. However, it does not explain what 'Bundle tier' means, how current the data is, or any limitations.

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 very short and front-loaded with the main subject. However, 'Bundle tier' is unexplained jargon that slightly reduces clarity; otherwise the sentence is tight and wastes no 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?

The output schema covers the return shape, and the zero-parameter schema lowers complexity. Still, the description omits practical context such as when to choose this over get_major_news or get_market_clock, and 'Bundle tier' is not clarified. Adequate but with clear gaps.

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 no parameter documentation is needed. The empty schema already covers everything, and 'Bundle tier' suggests a fixed bundled output requiring no arguments. Baseline for zero-parameter tools is 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource as high-impact economic events and adds the key differentiator of volatility forecasts, which distinguishes it from news-focused siblings like get_major_news. It lacks an explicit verb, but combined with the tool name 'get', the intent is reasonably 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?

There is no guidance on when to use this tool instead of alternatives. 'Bundle tier' hints at packaging but not at the appropriate use case. The agent receives no exclusions, prerequisites, or comparisons to sibling tools.

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

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

No annotations are provided, so the description carries the full burden. The 'Context only — never a trigger' clause discloses a non-obvious behavioral trait: this tool is passive and must not be used to drive a trade or alert decision. However, nothing else is disclosed about recency, source coverage, output shape, or failure behavior, which is a noticeable gap for a tool with zero annotation support.

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 entire description is nine well-placed words across two sentences. The resource ('MAJOR RSS headlines') is front-loaded, and the behavioral guardrail ('never a trigger') follows immediately. Every word earns its place with zero waste.

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 tool with an output schema present, the description provides enough to invoke it correctly and understand its general role. The output schema presumably documents the return structure, so the main missing piece is the source or selection criteria for what qualifies as 'MAJOR' headlines, which is 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 takes zero parameters, and the rubric grants a baseline of 4 in this case since there is nothing for the description to document. The input schema is an empty object, and the description correctly adds no parameter details that would be redundant or invented.

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 ('RSS headlines') with a scope qualifier ('MAJOR'), making the tool's purpose as a news-context fetcher clear. The clause 'never a trigger' and sibling names like check_alert_tradeable and get_latest_alert make the distinction from action-oriented tools apparent. It doesn't specify which RSS sources or what 'major' means, so the purpose is clear but slightly underspecified.

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?

'Context only' explicitly frames when to use the tool (for gathering background/news context) and 'never a trigger' is an explicit when-not. However, it does not name any alternative tools, even though over 18 siblings exist, so an agent must infer the routing from the exclusion rather than being pointed to a specific sibling.

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 burden of behavioral disclosure. It conveys that the tool reports session state and related windows, implying a read-only lookup, but does not explicitly state that it is non-destructive, nor mention any timing/caching nuances. This is acceptable for a zero-param getter but not rich behavioral context.

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 dense, front-loaded line with no filler. Every phrase — 'open/closed', 'force-flat time', 'lane windows' — adds information. It is an appropriately sized definition for a simple no-argument getter.

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 tool with an output schema, the description reasonably covers the semantic categories returned. It doesn't explain the meaning of 'force-flat time' or 'lane windows', but the output schema can carry return-value detail. It lacks usage context, though that is already penalized under usage guidelines.

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

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

There are zero parameters and schema coverage is 100%, so the description has no parameter semantics to add. The baseline of 4 is appropriate because there is nothing missing for invoking the tool with an empty argument object.

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 ('session state') and enumerates the specific outputs it provides: open/closed, force-flat time, and lane windows. Although it is a noun-fragment rather than a full verb phrase, the tool name starts with 'get', so the action is unambiguous. It is specific enough to distinguish it from other market-data 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?

No guidance is given about when to use this tool versus sibling tools, and no alternatives or exclusions are mentioned. The agent must infer from the name and output fields that this is the go-to source for session clock status, which is not explicitly stated.

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 of behavioral disclosure. It describes the card's contents but does not state that this is a read-only operation, whether it can return empty results, or any data freshness or availability behavior. The 'get' prefix implies read-only, but nothing beyond that is disclosed.

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 concise fragment, roughly ten words, and gets straight to the point. Every word adds signal about the card's contents. It could be improved with a verb and clearer sentence form, but it is appropriately sized for a parameterless tool.

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 tool with an output schema present, the description covers the core payload concept. However, the jargon 'Tier-0' is unexplained, and there is no mention of when the card is available (e.g., market hours, after close) or any fallback behavior. The output schema presumably fills return-value details, but usage context remains thin.

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 the input schema is an empty object, so schema coverage is trivially 100%. Per calibration, a zero-parameter tool gets a baseline of 4; the description adds clarifying content about what the returned card includes, which is sufficient.

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 resource ('Tier-0 morning desk card') and lists its key contents (rails, IV rank, gap, events), making it clear this is a composite daily overview. It is distinct from sibling tools like get_rails or get_iv, though it doesn't explicitly contrast itself. The lack of an explicit verb is a minor gap.

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 guidance on when to use this tool versus alternatives. It implies a morning desk use case but does not state conditions, exclusions, or mention any sibling tool. An agent must infer from the name and context.

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 burden of behavioral disclosure. It reveals that the score is dynamic and derived from spread plus tick variance, and flags Pro-tier access. However, it does not state whether the value is bounded, what higher/lower scores mean, or what the output contains, leaving notable gaps.

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 compact sentence that front-loads the core idea and adds the access note second. Every phrase contributes information, with no fluff or repetition.

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, has one optional parameter, and an output schema exists, so the description does not need to explain return values. It explains what the score is based on and Pro-tier access, but lacks usage context and score interpretation guidance, which an agent would benefit from.

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 0% and the description does not mention the 'instrument' parameter. However, the parameter is a single optional string with a clear name and default value (SPY), so semantic risk is low. The description adds no parameter-specific meaning, but the schema's title and default provide basic clarity.

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 computes a 'dynamic execution risk score' from 'spread + tick variance,' identifying the specific resource and method. It does not explicitly differentiate it from sibling tools, but the metric's composition is unique enough to disambiguate it from other get_* 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?

No guidance is provided about when to use this tool versus alternatives. The 'Pro tier' note hints at access restrictions but does not explain intended use cases, prerequisites, or situations where another tool would be more appropriate.

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?

There are no annotations, so the description carries the full burden, but it only states what the tool returns and gives no behavioral traits such as whether it performs computation, fetches live data, has side effects, or how the heuristic is derived. The name implies read-only, but the description adds little beyond that.

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. It is appropriately compact for a simple one-parameter getter, though the brevity comes at the cost of needed context.

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 low-complexity tool with one optional parameter and an output schema, the description is minimally viable: it identifies the resource and the symbol scope. However, it does not explain what the pin/magnet score means or when an agent should prefer this tool, so the context is incomplete for a non-domain-expert agent.

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 schema has one parameter, 'symbol', with 0% description coverage, but the description only repeats the word 'symbol' without explaining valid values, formatting, or the meaning of the default SPY. It does not compensate for the schema's lack of semantic detail.

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 exact resource ('Pin score / magnet heuristic') and ties it to a symbol, so an agent can tell this tool is for retrieving a pin/magnet reading for a single ticker. It is specific enough to stand apart from the many get_* siblings, though the jargon is not explained in plain language.

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?

No guidance is given for when to use this tool versus alternatives, nor any exclusions or prerequisites. The only implied usage is 'when you need a pin score,' but the description does not place it in a broader decision context among the sibling tools.

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

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

With no annotations, the description must carry the full burden. It does communicate that this is a read-style analytics tool and adds the useful access constraint 'Pro tier', plus the conceptual output of theta decay by session window. However, it does not disclose rate limits, authentication specifics, or anything about response shape beyond the existence of an output schema.

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 compact and front-loaded with the core purpose in the first sentence. The Pro tier note and structure enum are relevant, but the enum could have been formatted more cleanly as a list or valid-values note rather than a bare label.

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 one-parameter tool with an output schema, the description is adequate for a basic call: it names the tool's purpose, gives valid values, and notes Pro tier. It falls short on contextual completeness because it never clarifies the term 'premium compression', explains what a session window is, or differentiates this tool from adjacent analytics tools in the same suite.

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 schema description coverage is 0%, but the description compensates by enumerating the allowed structure values: iron_condor, vertical_spread_call, vertical_spread_put, single, short_call, short_put. It does not explain what each structure means or which one to choose for a given scenario, but it clearly identifies the valid inputs beyond the bare schema definition.

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 a Premium Compression Heatmap and specifies the metric: theta decay velocity by session window for a multi-leg structure. It is specific enough to distinguish this from most sibling analytics tools, though it does not explicitly contrast it with any named 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?

There is no guidance on when to use this tool versus the many option-related siblings like get_gex_profile, get_skew, or get_rails. The description implies use when theta decay compression data is needed, but it provides no exclusions, prerequisites beyond 'Pro tier', or alternative routing.

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?

There are no annotations, so the description bears the full burden of behavioral disclosure. It conveys that the output is a live gamma map with specific elements, but it does not disclose data source, update cadence, market-hours dependencies, or any caveats about the 'magnet' or 'flip' indicators. The output schema may help, but the description itself remains thin.

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 packed sentence that front-loads the key resource and its distinguishing content elements. There is no wasted wording, and given the zero-parameter input schema, this level of brevity is appropriate.

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 covers the core subject but leaves significant context gaps: it does not explain the jargon ('walls, flip, magnet, regime'), specify when the data is meaningful, or differentiate from closely related gamma tools. The presence of an output schema helps with return structure, but the lack of usage context and behavioral caveats makes this incomplete for an agent choosing among many similar market-analysis tools.

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 parameter semantics are effectively moot. The description does not need to explain inputs, and the simple factual label is sufficient for a no-argument call.

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 ('SPY 0DTE gamma map') and lists the key content dimensions ('walls, flip, magnet, regime'), making the purpose reasonably clear. It distinguishes itself from generic tools, though it does not explicitly contrast with siblings like get_gex_profile or get_pin.

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?

No guidance is given about when to use this tool versus alternatives such as get_gex_profile, get_pin, or get_path_risk_score. The phrases 'Live SPY 0DTE' imply a real-time use case, but there is no explicit when-to-use, when-not-to-use, or alternative routing information.

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 behavioral disclosure burden. It only states 'educational replay', which hints at non-actionable or historical context, but does not explain data recency, scoring semantics, absence behavior, or why a caller might need this versus live tools.

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 compact sentence with no filler. The temporal scope is front-loaded and the 'educational replay' qualifier adds useful context without bloating the definition.

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 read-only timeline with an output schema, the core idea is present, but the description is too thin: it omits parameter semantics and usage routing, and offers no behavioral context that the agent could not infer from the tool name alone.

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 0%, and the description mentions neither limit nor min_score. It does not explain how these parameters affect the returned timeline, leaving the agent to guess from names and defaults alone.

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: today's timeline of graded candidates, with an 'educational replay' qualifier. This distinguishes it from get_hist_replay on temporal scope, though it lacks a direct verb and leaves 'graded candidates' somewhat ambiguous.

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?

No guidance is given for when to use this tool versus siblings like get_hist_replay, get_morning_desk, or get_latest_alert. The temporal 'today' hint is helpful, but there is no explicit context or exclusion criteria.

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

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

With no annotations, the description carries the behavioral disclosure burden. It does add value by naming the three output regime buckets and the HAR-lite model, but it does not disclose staleness, lookback window, limitations, or any other behavioral detail.

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-loaded with the model and output categories. The 'not Trapdoor wall trust' phrase is cryptic and may not earn its place, but the overall length and ordering are appropriate.

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 zero annotations and a cryptic one-line description, an agent cannot confidently determine when to invoke this tool or how to interpret the result semantically. The output schema helps with return shape, but not with the meaning of the regime buckets, data scope, or invocation context.

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

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

Schema description coverage is 0%, and the description says nothing about the 'symbol' parameter. The parameter is self-evident from its name and default value, but the description still fails to add any guidance on accepted symbols or behavior when omitted.

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 the resource (realized volatility) and the output classification (Calm / Elevated / Explosive), which is more specific than the name alone. However, it relies on unexplained jargon such as 'HAR-lite' and 'Trapdoor wall trust' and does not explicitly say it returns a regime classification.

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 guidance on when to use this tool versus its many get_* siblings. The parenthetical 'not Trapdoor wall trust' hints at a distinction but provides no actionable context for an agent deciding between tools.

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

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

With no annotations, the description carries the full burden. It does not disclose whether this is a read-only operation, what the 'UW chain' source implies, whether the flag is computed or stored, or any latency/rate considerations. The phrase 'from the UW chain' hints at a data source but adds little behavioral clarity.

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 compact sentence with no filler. It front-loads the core concept. However, it is so terse that it sacrifices clarity for brevity, so it does not earn a 5.

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 has an output schema, so return values may be documented there, but the description still lacks context about what the wing-fattening flag means, how to interpret the skew strip, and when this tool is relevant. For a niche options tool with no annotations, this is a meaningful 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 0%, so the description must compensate. It does not explain the 'symbol' parameter at all, though the parameter name and default 'SPY' are self-explanatory. The description adds no meaning about how symbol affects the skew strip or wing-fattening flag. Baseline is 3 because the single parameter is trivially inferable.

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 'IV smile / skew strip + wing-fattening flag from the UW chain' identifies a specific resource (IV smile/skew strip) and a derived flag (wing-fattening), and the verb is implied as retrieving. It is somewhat jargon-heavy and does not clearly distinguish it from siblings like get_rails or get_gex_profile, but it does convey a distinct options-market 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?

No guidance is given about when to use this tool versus alternatives. The description does not mention any conditions, exclusions, or related sibling tools. An agent would have to infer usage from the name and jargon.

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

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It does not state whether this is a read-only lookup, what data source it pulls from, how the divergence is computed, what the output represents, or any other behavioral detail.

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 extremely terse, but it is under-specified rather than appropriately concise. 'SPY↔QQQ rails divergence feather' is not a complete statement of purpose or behavior, so the brevity does not serve the 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?

Despite an output schema existing, the description still fails to explain the tool's core function, expected use, or relationship to sibling indicators. This is effectively an opaque label, and the agent would need external knowledge to call or interpret this tool 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 input schema carries no burden and the description does not need to explain parameter semantics. The baseline of 4 applies because there is nothing missing on this dimension.

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 gives a resource ('SPY↔QQQ rails divergence') but no clear verb or explanation of what the tool actually does. Terms like 'feather' and 'rails' are unexplained jargon, making the purpose ambiguous. It does not meaningfully distinguish itself from sibling tools such as get_vrp_divergence or get_cross_asset.

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 guidance on when to use this tool versus any of its many siblings. The description is a bare phrase with no context, use cases, or exclusions, so an agent has no way to choose it over the related divergence and market indicator tools.

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

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

No annotations are provided, so the description carries the full burden. It discloses key behavioral traits: the expiry selection rule, the 5–45 DTE window, the explicit 0DTE exclusion, and the Bundle/Pro access requirement.

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 tight, front-loaded sentence contains all essential information: data type, expiry selection, exclusion, and access tier. There is no filler or repetition.

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?

An output schema exists, so return shape does not need describing. The description covers the main decision-relevant details: what is returned, on which expiry, and what access is required. It only lacks explicit routing among sibling tools.

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 0% and the description adds no direct parameter guidance. However, the only parameter is a common 'symbol' field with a default of SPY, which is self-explanatory to an agent, so the lack of elaboration is not a major obstacle.

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 and resource: it gets weekly/swing gamma walls plus 1σ EM on the nearest 5–45 DTE expiry. It also differentiates itself from intraday/0DTE tools by explicitly saying 'not 0DTE' and using 'swing'.

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 this is for swing/weekly horizon gamma analysis and explicitly excludes 0DTE, which helps with timing. However, it does not name sibling alternatives or explain when to choose this over related tools like get_daily_structure or get_gex_profile.

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 and does useful work: it exposes freshness fields to check, warns that OFI is not candle-close synchronized, and clarifies that |OFI| >= 0.30 is interpretive context rather than an entry gate or exit/re-entry signal. It omits auth, caching, or rate-limit behavior, but the interpretive caveats are genuinely valuable and not derivable from structured fields.

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 lines are front-loaded with what the snapshot contains, then the freshness check, then the OFI interpretation caveat — each sentence earns its place. Density of jargon slightly reduces readability, but 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?

An output schema exists, so return values need not be explained. For a zero-parameter snapshot tool the description covers the essentials: what is returned, how to judge staleness, and how to interpret the OFI figure. Only cross-tool routing guidance 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 zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-parameter tool applies. The schema requires no additional explanation.

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 (the latest Confluence Tape snapshot) and enumerates its contents (rolling ofi_5m, tape_5m, quadrant), so an agent knows what it retrieves. It offers no differentiation from siblings like get_cvd_liquidity or get_gex_profile, and the domain jargon ('tape', 'quadrant') may not be self-explanatory.

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 gives a concrete operational instruction — verify ts/updated_at, age_sec and stale before trusting the data after a closed candle — which implies when the snapshot is usable. It does not state when to prefer this tool over sibling market-data tools or name an alternative, leaving selection to 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not state whether the tool is read-only, whether it computes or fetches data, or what operational constraints apply. 'Bundle tier' hints at access level but does not explain 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 compact line with no filler. The opening label 'VRP Divergence Index' immediately communicates the core concept. 'Bundle tier' is cryptic but does not bloat the text.

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 tool with an output schema available, the description provides the essential metric definition needed to select and invoke the tool. It could add interpretation or eligibility context, but the minimal invocation surface makes this largely 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 input schema has zero parameters, so there is nothing for the description to clarify. Baseline 4 for zero-parameter tools is appropriate; the metric definition is sufficient.

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 metric, 'VRP Divergence Index', and defines it as 'ATM straddle IV vs realized variance', which clearly identifies the tool's purpose. It is distinguishable from the sibling set by naming a distinct volatility-risk-premium concept, though 'Bundle tier' adds little clarity.

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 metric definition: an agent would select this when it needs the VRP divergence index. However, the description does not explicitly say when to prefer it over related siblings such as get_rv_regime or get_premium_compression_data, nor does it give 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?

There are no annotations, so the description carries the behavioral burden. It does disclose useful behavioral context: the data is 'Delayed' and sourced from 'official FRED'. However, it does not mention units, update cadence, or whether 2s10s is a spread, leaving some behavioral ambiguity.

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 compact, front-loaded phrase that uses every word meaningfully: delay status, source, and exact tenor composition. There is no filler or redundant restating of the schema.

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 tool with an output schema present, the description gives enough context: source, latency, and exact series. The only real gap is explicit usage routing, which was already penalized in usage guidelines, so the tool remains adequately specified for an agent to call it confidently.

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 nothing for the description to clarify beyond the schema. This earns the baseline of 4; no parameter documentation is needed or expected.

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 exact financial resource: official FRED 10Y / 2Y / 2s10s yield curve data. Even though it lacks an explicit verb, the tool name 'get_yield_curve' plus this resource specificity makes the purpose unmistakable and distinct from sibling 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?

The description implies the tool should be used when the agent needs FRED 10Y/2Y/2s10s curve data, but it does not explicitly state when to use it versus alternatives or when not to use it. With many market-data siblings, some explicit routing guidance would strengthen this dimension.

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 behavioral burden. It usefully discloses that the stored 0–100 score may be null (unscored) and that scores are not refreshed when history is read, which is genuine behavioral context, but it omits read-only status, ordering guarantees beyond 'newest first', and any auth or rate-limit notes.

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 text is short but poorly front-loaded and cryptic: 'trapdoor' is used without definition and the clause 'Match ts, symbol, direction and level' lists output fields that the existing output schema already covers. Structure obscures rather than aids comprehension.

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?

An output schema exists so return-value explanation is not required, but two undocumented parameters at 0% coverage go unaddressed and the description never clarifies the score scale mismatch. For a 2-parameter tool with no annotations, this leaves key invocation details 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?

Schema description coverage is 0% for both parameters, so the description must compensate and does not. 'limit' is never mentioned, and 'min_score' (default 6) is not explained — worse, the description states scores are 0–100 while a default of 6 implies a small scale, creating ambiguity about the filter's units.

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 conveys that it lists today's Discord-sourced A+/B alerts in an alerts[] array, newest first, which identifies the verb and resource. However it leans on unexplained jargon ('trapdoor', 'A+/B') and never states plainly that this is a historical alert list, leaving the purpose only partially 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?

There is no guidance on when to use this tool versus the obvious sibling get_latest_alert, nor any statement of prerequisites or exclusions. The only scoping hint is the implicit 'Today's' window, which is inferred rather than framed as usage direction.

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

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

No annotations are provided, so the description must disclose behavior. It does: the tool is advisory only, requires an external server and API keys, and does not finalize an order without user confirmation. This addresses the most important concern for a trading tool, even though it does not detail error cases or 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 the core purpose, followed by essential execution and safety context. Every sentence adds value; 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?

An output schema exists, so return-value details are not required. The description covers prerequisites, advisory behavior, and user confirmation, but leaves the semantics of alert_json and use_latest ambiguous enough that an agent could invoke the tool incorrectly, despite both parameters having defaults.

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 0%, so the description needed to explain the two parameters. 'from alert' loosely suggests alert_json, but use_latest is entirely unexplained, and the relationship between the two parameters is not described. The description fails to compensate for the schema gap.

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 ('Build') and a clear resource ('Alpaca execution plan from alert'). The broker and tool family are unambiguous, and it distinguishes itself from sibling plan_ibkr_entry, plan_robinhood_entry, etc. simply by naming Alpaca.

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 useful context: pair with uvx alpaca-mcp-server, requires ALPACA_API_KEY/SECRET, user confirms place_option_order, and the tool is advisory only. It does not explicitly state 'use only for Alpaca accounts' or contrast with non-Alpaca plan tools, but the naming and context make that reasonably clear.

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 behavioral disclosure burden. 'Advisory only' is a meaningful, explicit disclosure that the tool does not execute trades, and the broker-following sentence reveals how behavior adapts per broker. The term 'Pro gates + structure' is jargon-y and not fully unpacked, which keeps this 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?

The description is extremely compact: purpose, broker contract, behavioral routing, and advisory caveat are each in short, front-loaded statements. No filler or repeated schema content.

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 output schema covers return shape and the description covers purpose and advisory behavior, so the tool is minimally callable. However, the undefined alert_json and use_latest parameters remain a significant gap for an agent trying to invoke it with meaningful input, and no explicit guidance is given for choosing broker-specific siblings.

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 0%, so the description must compensate. It does add meaning for the broker parameter by enumerating valid values and explaining that MCP sequence and price_source follow the broker, but alert_json and use_latest are completely unexplained, leaving most of the invocation semantics to guesswork.

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 action and resource: producing a broker-agnostic entry plan. The 'broker-agnostic' qualifier and supported-broker list distinguish it from the six broker-specific plan_*_entry siblings without needing to open their schemas.

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 makes the use context clear: this tool works for any of the listed brokers, and the broker selection drives MCP sequence and price_source. It does not explicitly enumerate when to choose this over plan_robinhood_entry or plan_ibkr_entry, so it lacks an explicit exclusion, but the broker-agnostic framing supplies enough context.

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, and it does well: 'drafts instructions only; user Review & Submit' and 'Advisory only' disclose the critical behavioral trait that this tool does not place trades or execute actions — it only produces a plan for human review. This is essential context that prevents an agent from assuming live order placement.

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 compact and front-loaded with the purpose before the workflow caveats. The only questionable element is the embedded API URL, which adds marginal value to an agent's decision-making and could be trimmed, but overall the text is efficient with no wasted sentences.

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 workflow context (advisory-only, draft instructions, pairing with IBKR API) is well covered, and an output schema exists so return values need no description. However, with 0% parameter coverage and an output schema present, the description should at least hint at what alert_json should contain and what use_latest controls. For a 2-parameter advisory tool this is moderately complete but leaves the input semantics to inference.

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 0%, so the description must compensate for the two undocumented parameters (alert_json, use_latest). It does not. The phrase 'from alert' hints that alert_json is the input alert, but no format, structure, or meaning is given for either parameter, and use_latest is entirely unexplained. This is a significant gap for a 0%-coverage 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 verb and resource ('Build Interactive Brokers execution plan from alert'). The broker-specific naming clearly differentiates it from sibling plan tools (plan_alpaca_entry, plan_robinhood_entry, plan_webull_entry, plan_tastytrade_entry, plan_entry) without needing to open their schemas. An agent can immediately tell which broker workflow this serves.

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 workflow context: it pairs with the IBKR public API, drafts instructions only, and requires user Review & Submit in IBKR AI Instructions. 'Advisory only' sets proper expectations. It doesn't explicitly name alternatives or state when-not-to-use, but the broker-specific naming and 'advisory only' framing provide adequate 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, the description carries the safety burden, and it does so by clearly stating 'Advisory only — does not place orders,' which is the most important behavioral trait for an execution-planning tool. It also hints at the output behavior by listing the plan components. It does not mention authentication or external calls, but for a read-only planner this is a reasonable disclosure.

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

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

Two sentences, with the main action and plan contents front-loaded and the advisory/safety caveat in the second sentence. There is no filler or repetition.

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 output schema and the listed plan components cover what the tool returns, so return-value explanation is not needed. However, the tool's parameter semantics—especially use_latest versus alert_json—are left unexplained, which is a real gap for correct invocation despite the clear purpose.

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 0%, so the description needed to explain alert_json and use_latest, but it only says 'from alert' and never clarifies the interaction between the two parameters. The boolean use_latest with default true is particularly ambiguous: does it override alert_json, and when should an agent pass alert_json explicitly? The description does not compensate for the schema's lack of descriptions.

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 action and resource: 'Build Robinhood execution plan from alert,' which clearly distinguishes it from the sibling plan_* tools by broker. It also enumerates the plan contents (delta band, spread gate, budget, bracket, MCP steps) and states the advisory nature.

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 explicitly frames the tool as advisory-only and instructs pairing with robinhood-trading MCP for actual execution, which tells the agent when this planning stage is appropriate and that order placement is out of scope. It does not explicitly name sibling alternatives like plan_alpaca_entry, but the broker-specific naming makes the routing clear.

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 and discloses the most safety-critical trait: 'Advisory only — user confirms every place' tells the agent this tool never autonomously places orders. It also signals environment-dependent behavior via TASTYTRADE_ENV=sandbox and maps the downstream dry_run → confirmation_token → place_order flow. It stops short of detailing side effects such as network calls 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?

Four short sentences, each with a distinct job: purpose, pipeline position, environment guidance, and safety behavior. No filler, and the most important information (what the tool builds) 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?

The output schema covers return values, and default parameter values reduce invocation risk, but the parameter semantics gap is real: with 0% schema coverage, an agent cannot know what alert_json should contain or what use_latest=true toggles. The workflow and safety guidance are strong enough that missing parameter documentation is the only notable omission.

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 0%, and the description barely compensates: 'from alert' hints that alert_json carries the alert payload, but the expected format is never specified. use_latest is entirely unexplained in both the schema and the description.

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+resource pair: 'Build tastytrade execution plan from alert.' The 'tastytrade' qualifier clearly distinguishes this from the sibling broker planners (plan_ibkr_entry, plan_alpaca_entry, plan_robinhood_entry, plan_webull_entry), though it never explicitly names or contrasts them.

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 strong workflow context: 'Pair with self-hosted tastytrade-mcp (dry_run → confirmation_token → place_order)' positions this tool as the entry step of an execution pipeline, and 'Start with TASTYTRADE_ENV=sandbox' prescribes the safe starting environment. It does not, however, state when to choose this over the generic plan_entry or other broker-specific planners.

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 disclosure burden and does well: it states 'Advisory only — does not place orders,' distinguishes the OAuth cloud flow from the local App Key flow, and mentions 'preview_option_order then place.' It omits details like rate limits or auth failure behavior, but the core mutation boundaries are clear.

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 compact and purposeful: four short lines, with the primary purpose front-loaded and each subsequent line adding meaningful detail. The local-mode line is technical but necessary for correct invocation.

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 covers the tool's purpose, advisory-only status, and mode details, while the output schema exists to explain returns. However, it lacks semantics for alert_json and use_latest, which are both central to a planning tool, and it does not clarify what data the alert must contain. This makes the definition only moderately complete for first-time 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?

Schema description coverage is 0%, so the description must compensate. It richly explains 'mode' with defaults, endpoints, and auth flows, but 'alert_json' and 'use_latest' receive no direct explanation or format guidance. One of three parameters is well covered; the other two are left to inference, leaving a notable gap for schema-description-poor tooling.

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 verb and resource: 'Build Webull execution plan from alert.' It also clarifies the advisory nature upfront ('does not place orders') and ties it to a sibling by noting 'same structure/risk as Robinhood,' so an agent can distinguish it from other plan_* 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?

The description gives explicit mode-selection guidance: cloud vs local, with OAuth/App Key and the confirming-app flow. It does not explicitly state when to choose this over plan_robinhood_entry or plan_ibkr_entry, but the Webull-specific context and sibling naming make the intent clear.

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

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It only names the content ('min score and session window') but does not say whether this is a static reference, a computed summary, or how the values relate to alert generation. With zero annotation coverage and no behavioral detail, this is a significant gap.

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 concise sentence that front-loads the core resource ('Pro alert criteria') and immediately specifies the two key pieces of information. It contains no padding, repetition, or irrelevant detail.

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 tool with an output schema present, the description is largely complete: it tells an agent what topic the output covers. The main shortfall is the lack of any contextual framing about how 'min score' and 'session window' relate to the pro alert system, but the output schema can carry the detailed return structure.

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 schema description coverage is 100%, so the schema fully documents the input surface. The description adds meaning about what the output covers, which is appropriate. The baseline for 0-parameter tools is 4, and nothing here reduces that.

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 ('Pro alert criteria') and the key content ('min score and session window'), which is distinct from the sibling tools that retrieve live alerts or check tradeability. However, it lacks an explicit verb like 'returns' or 'summarizes', so the action 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?

There is no guidance on when to use this tool versus alternatives such as get_latest_alert or check_alert_tradeable. The description implies this tool provides criteria definitions, but it does not state a use case, prerequisites, or exclusions.

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