SCRIPTMASTERLABS — PRO-LO

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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds a genuinely valuable caveat beyond the annotations: sentiment data is not wired and the narrative side is a disclosed proxy, warning the agent not to treat output as literal sentiment. It stops short of describing output shape or confidence handling.

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

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

Two sentences with no filler, and the core comparison is front-loaded. The second sentence is dense and repeats the proxy disclosure twice ('disclosed as a proxy, not literal sentiment measurement'), which is slightly redundant.

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

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

With no output schema, the description carries the burden of conveying what the comparison yields, but it never says what the result looks like (a divergence score, a verdict, a directional signal) or how the two sides are weighted. The proxy caveat helps, but an agent still cannot predict the response when calling it.

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

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

Schema description coverage is 100%, with ticker and timeHorizonDays (default 90) both documented, so the baseline is 3. The description adds no extra detail on how timeHorizonDays affects the comparison window or what ticker formats are accepted beyond the schema examples.

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 two things compared — real fundamental signals (P/E, reference data) versus a momentum/volatility proxy for narrative intensity — which is more specific than restating the name. It does not explicitly differentiate from siblings like track_volatility_surface or mandelbrot_fractal_analysis, so an agent must infer that this tool is the fundamental-vs-narrative comparison.

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 statement of when to use this tool, when not to, or which sibling to prefer for related analysis (e.g. volatility surface or fractal analysis). The agent gets a definition of the computation but no 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?

Annotations already declare read-only, idempotent, open-world behavior, so the safety profile is covered. The description adds useful context about external source dependencies (Tradier/Polygon, SEC FTD, SqueezeOS oracle), but omits rate limits, latency, failure modes, or what 'classify' actually entails.

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?

It is a single sentence with no filler, but it is a dense noun phrase that front-loads data sources rather than the tool's action. The structure could be improved by leading with what the tool does.

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 classification tool with no output schema, the description fails to explain the output categories, thresholds, or how the GEX and FTD data combine into a regime. An agent cannot know what a successful response looks like or how to interpret it.

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

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

Schema coverage is 100% for the single ticker parameter, so the schema already documents it fully. The description adds no additional meaning about the ticker parameter or any formatting expectations. Baseline 3 is appropriate when the schema does all the work.

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 specific data sources and metrics (dealer GEX from Tradier/Polygon, Reg SHO threshold status from SEC/SqueezeOS), but it never states the action of classifying a microstructure regime or what the classification output represents. It also fails to distinguish itself from sibling track_gamma_squeeze_mechanics, which also concerns gamma exposure.

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 indication of when to use this tool versus alternatives, no prerequisites, no exclusions, and no explanation of how the two data sources should factor into a decision. The description is purely descriptive of underlying data.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's job is to add context, and it does: it discloses the exact return shape (per-path direction and confidence, coherence score, pass/block gate) and bounds the scope by stating the Jev review is out of band. It omits any mention of latency, x402 payment/access requirements hinted at by 'mcp-x402', or how thresholds are set.

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

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

Three sentences, front-loaded with what the tool does and the signal paths, then the return contents, then the scope caveat. It is dense but jargon-heavy (PRO-LO, SqueezeOS, SML Triple-Trigger, mcp-x402), which costs some readability without wasting 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?

With no output schema, the description carries the burden of explaining returns, and it does so adequately: paths, direction, confidence, coherence score, and gate result. Missing pieces are how to interpret the coherence score's threshold and the ambiguity around the Jev sibling, but an agent has enough to call it 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?

Only one parameter, and the schema already documents it at 100% coverage ('Stock ticker symbol'). The description reinforces the singular-ticker scope ('for one ticker'), which is mildly useful for preventing multi-ticker batching, but adds no format, exchange, or case-sensitivity detail beyond the schema. Baseline 3 applies.

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

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

The description names a specific operation (multi-path consensus for a single ticker) and enumerates the four independent signal paths it consults (trade-engine composite, SMA20/50 trend, SqueezeOS picks, SML Triple-Trigger), which is far beyond restating the name. It also implicitly distinguishes itself from coherence_jev_verdict by scoping itself to the coherent gate rather than the Jev review, though that distinction is blurred by the odd claim that Jev review 'is not run over MCP' when a Jev sibling tool exists.

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: an agent can infer this is the tool for 'do my directional signals agree on ticker X', and the closing sentence rules out expecting a Jev/TypeSafe verdict. However, there is no explicit statement of when to prefer this over coherence_jev_verdict, earnings_gate_verdict, or the individual signal tools, and no prerequisite or exclusion 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?

The description calls this a read-only decision product, but annotations declare readOnlyHint=false, which is a direct contradiction. The description otherwise adds useful behavioral detail such as pricing, abstention behavior, and Jev key handling, but the annotation contradiction forces a 1.

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 dense but front-loaded with the core product, cost, and verdict logic. The parenthetical technical details are useful for understanding the decision rule, though the single paragraph could be more structured.

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 complex paid decision tool with no output schema, it explains the verdict logic, family requirement, path abstention behavior, and Jev key limitation. It lacks sibling routing guidance, but the core invocation context is 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?

Schema description coverage is 100%, so ticker, claim, and action are already documented in the schema. The description confirms ticker scope and echo behavior but adds no parameter syntax or constraints beyond that baseline.

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: computes PRO-LO multi-path coherence for a ticker and adds a Jev review. The PASS/DENY definition makes the product distinct from generic analysis siblings, even without naming 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?

There is no explicit when-to-use, when-not-to-use, or alternative routing guidance among siblings such as coherence_gate_review or earnings_gate_verdict. Usage is only implied by calling it a decision product and listing verdict 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?

Goes far beyond the annotations: discloses the price and payment rail, the exact PASS predicate (coherence >= 0.6, >= 2 agreeing paths spanning >= 2 families), abstention semantics ('they never vote' and are named in output), the Jev review behavior when unconfigured, and the shadow/non-executing posture. These are behavior facts an agent could not derive from readOnlyHint=false or openWorldHint=true.

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

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

Front-loads the price and the purpose, then the four families, then the verdict rule. Dense em-dash stacking makes some clauses hard to parse, but no sentence is filler.

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

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

With no output schema, the description carries the return value and it does so thoroughly: the verdict token, the gate criteria, the abstained-path list, the Jev status field semantics, and decision_eligible. An agent has enough to call it and interpret the response.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds a little: it establishes that paths are anchored to an earnings print and that the gate is pre-earnings, but the fallback-to-Finnhub-calendar detail lives in the schema itself rather than the description. Modestly above baseline.

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

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

States a specific verb+resource ('pre-earnings coherence gate' computing a fleet coherence verdict from four named paths) and defines exactly what the tool returns: PASS or DENY. The decision vocabulary and the four data families make it unmistakable what this tool does.

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?

Gives clear invocation context: it is a paid x402 gate (0.25 RLUSD), it is SHADOW with decision_eligible=false, and it executes nothing. However, it never says when to prefer it over the closely named siblings coherence_gate_review, coherence_jev_verdict, or coherence_jev_verdict-style review, so the routing decision is left 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?

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so safety is covered. The description adds one genuinely useful trait beyond them — that grounding data is live-fetched and no invented inputs reach the model — but says nothing about non-determinism of model output, latency, cost, or how the live fetch behaves on failure.

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

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

A single well-formed sentence with no filler, and the key constraint (live data grounding) is front-loaded. It is efficient, though its brevity is closer to under-specification than to disciplined terseness.

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

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

With no output schema, the description should say something about what comes back from the model invocation, and it does not. Parameters and annotations are otherwise adequately covered, so this is minimum-viable rather than inadequate.

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

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

Schema description coverage is 100%, so both parameters (ticker, focusQuestion) are already documented and the baseline is 3. The description adds no additional meaning about how these parameters shape the call, such as whether focusQuestion is optional or how it steers the reasoning.

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 mechanism (invokes Google Gemini) and the input condition (real, live-fetched market data as grounding), but never states what the tool actually produces — reasoning, verdict, narrative, or price target. It does not distinguish itself from siblings like analyze_narrative_divergence or coherence_jev_verdict, which likely also consume market data.

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 when-to-use or when-not-to-use guidance, and no sibling is named as an alternative. The only implied usage signal is that it requires a ticker, which the schema already says.

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

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

Annotations already declare readOnly, idempotent, open-world, non-destructive behavior, so the bar is lower. The description adds meaningful context beyond annotations: the verdict is a 'disclosed-heuristic', contracts come from a 'real fetched chain', and contracts are 'never invented'. It does not cover failure modes, rate limits, or freshness guarantees, so not a 5.

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

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

The description is a single front-loaded sentence that leads with the main action and then qualifies the contract-selection behavior. It is dense but every clause (real strike/expiration/bid-ask/greeks, never invented) carries information. Slightly heavy em-dash phrasing keeps it from 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?

With only two parameters, no output schema, and readOnly annotations, the description should do more to explain the returned structure – for example whether it returns a single verdict plus one contract, a list of contracts, or confidence metadata. It also leaves the 'target delta band' ambiguous since no corresponding input exists. It is adequate but has 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?

Schema description coverage is 100%, so both parameters (ticker, timeHorizon) are fully documented in the schema and the baseline is 3. The description adds no parameter-level detail and introduces a 'target delta band' that does not map to any input parameter, which could confuse an agent about how the delta target is supplied.

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

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

The description states specific verbs and resources: it generates a BUY/SELL/HOLD verdict and selects real listed option contracts nearest a target delta band from a fetched chain. An agent can distinguish this from pure analysis siblings because it combines a signal with concrete contract selection. It does not explicitly name a sibling alternative, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the name and the phrase 'trade execution signals' – there is no explicit 'use when' context, no exclusions, and no routing to alternatives such as the volatility-surface or microstructure tools. The agent can infer this is for actionable trade ideas, but must guess the boundaries.

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

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds genuine context beyond that: the data source (Polygon grouped-daily aggregates) and the fact that results are fused with per-symbol GEX/Hurst/IV-surface computations. It stops short of disclosing scan cost, latency, universe size, or result shape.

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

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

It is a single sentence, but it is dense and self-referential ('engines above') rather than front-loaded with a plain statement of what the scan does. No waste in length, but the structure prioritizes technical provenance over the agent's immediate need.

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?

There is no output schema, so the description must explain what the scan returns — result shape, per-symbol fields, or universe breadth — and it does not. For a tool with no required params and no output schema, an agent still cannot predict the response, which is a material gap.

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

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

Schema description coverage is 100% and the single filterRegime parameter already enumerates ALL/SQUEEZE/FRACTAL/SKEW in the schema. The description adds nothing about what these regimes mean or how filtering changes results, so the baseline 3 applies.

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

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

States a specific operation (wide-market scan) over a specific resource (the real US equity universe via Polygon grouped-daily aggregates), and explicitly contrasts it with a fixed short symbol list, which distinguishes it from symbol-pinned siblings. The phrasing 'fused with the real per-symbol GEX/Hurst/IV-surface engines above' is jargon-heavy and refers to tools not visible in the sibling list, slightly muddying the boundary.

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 only an implicit contrast ('not a fixed short symbol list, no pinned symbols') and no explicit statement of when to choose this scan over analyze_narrative_divergence, track_gamma_squeeze_mechanics, or any other sibling. No prerequisites, no exclusions, no cost/latency warning despite it being a wide-universe scan.

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

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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds genuinely new behavioral context: the computation runs across five fixed timeframes, and the tool abstains on the Hölder spectrum because tick-level history is not ingested. That abstention contract is the kind of thing an agent cannot learn from structured fields. Missing only return shape or failure modes.

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

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

Three sentences, core computation front-loaded, with the limitation last. Slight waste from the repeated filler 'real' ('Real Rescaled-Range ... at each real timeframe ... real excess kurtosis of the real return series'), which crowds out useful 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 read-only single-parameter analysis tool with no output schema, the description says what is computed, over which timeframes, and what is deliberately not computed. An agent knows enough to call it correctly; the only gap is the exact response structure and how short-history tickers are handled.

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

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

There is a single parameter with 100% schema description coverage (ticker with examples), so the schema does the work. The description adds nothing about ticker semantics (e.g. whether unsupported tickers or short histories cause abstention), so the baseline 3 applies rather than higher.

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

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

Names the concrete metric (Rescaled-Range Hurst exponent) and the data source (historical bars at 15M/1H/4H/1D/1W), plus excess kurtosis of the return series — specific verb+resource. It does not, however, contrast itself with any sibling (e.g. track_volatility_surface or classify_microstructure_regime), so an agent must infer which analysis tool to pick.

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 negative scope statement ('Does not compute a true Hölder singularity spectrum — abstains rather than fabricating one') usefully bounds expectations, but there is no positive guidance on when to call this versus the many other analysis/scanner siblings, and no prerequisites or cost/rate 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?

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), so the bar is lower, and the description adds genuinely new behavioral context: the scenario set is static and pre-defined, and the projected impact is a heuristic model rather than a prediction. It stops short of describing what the response contains (direction, magnitude, confidence).

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, zero filler. The core action is front-loaded and the epistemic caveat follows immediately as the most important qualifier.

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

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

With no output schema, the description carries the burden of explaining what comes back, and it does so only at a conceptual level (heuristic projected impact). For a read-only, two-parameter tool this is close to complete, but the shape of the result remains unspecified.

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

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

Schema coverage is 100%, so baseline would be 3, but the description adds real meaning by establishing that scenarioId comes from a fixed, pre-defined catalog — i.e., no custom or ad-hoc scenarios are accepted, which the enum alone does not state. The ticker parameter's role as the 'real live quote' target is also clarified.

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: it runs a pre-defined hypothetical shock scenario against a real live quote. The scope (static catalog, hypothetical vs. live price) makes it easy to tell apart from siblings like track_volatility_surface or generate_trade_execution_signals, though it never names an alternative explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the phrase 'hypothetical shock scenario ... against a real live quote' suggests stress-testing a position or ticker, but there is no explicit when-to-use, when-not-to-use, or routing guidance relative to the many analysis siblings.

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

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description does add genuine value by disclosing data provenance (GEX plus SEC FTD) and explicitly flagging that the FTD signal is a proxy for short-selling pressure rather than true short interest, which affects interpretation. It says nothing about score range, refresh cadence, or output shape, so it stops short of 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?

It is a single sentence with no filler, but it is dense with unexplained proprietary terms ('SqueezeOS', 'chain-derived GEX') that force the agent to parse rather than act. The caveat is useful but buried at the tail rather than 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?

With no output schema and only safety annotations, the description carries the burden of explaining what comes back, and it never states the score's scale, components, or return format. The provenance and proxy disclosure are the right kind of content, but an agent still does not know how to read or threshold the result.

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

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

There is a single required parameter with 100% schema description coverage ('Stock ticker symbol'), so the schema already carries the semantics. The description adds no guidance on ticker format, exchange suffixes, or symbol validity, which is the baseline expectation at full coverage.

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

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

The description names a specific computed artifact (a squeeze-pressure score) and its two inputs (chain-derived GEX and SEC fails-to-deliver), which lets an agent tell it apart from generic regime or volatility siblings. The verb is implied by 'track' in the name rather than stated, and heavy proprietary jargon ('SqueezeOS FTD oracle') adds noise rather than 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?

There is no statement of when to use this tool versus alternatives such as track_volatility_surface, classify_microstructure_regime, or live_universe_scanner_scan. An agent must infer usage purely from the score's subject matter, and no prerequisites or exclusions are given.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world). The description adds genuinely useful context beyond them: the data provenance guarantee that every grid point is a real listed contract rather than interpolated, which tells the agent this is a fidelity-critical data source. It stops short of stating latency, caching, or how many expirations are included.

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

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

One sentence with no filler beyond the thrice-repeated 'real', which does emphasize the anti-fabrication guarantee but reads as insistence rather than specification. The sentence is not front-loaded with a verb, so the agent parses the artifact before the action.

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

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

With no output schema, the description is the only source of information about what comes back, yet it never describes the grid's axes (strikes vs. expirations), shape, or return structure. For a read-only one-parameter tool this is adequate to select it, but not to know what to expect in the payload.

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

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

There is a single parameter, ticker, and the schema already documents it at 100% coverage, so the description carries little extra burden. The description adds nothing about ticker format (exchange suffix, case) or option-chain availability constraints; baseline 3 applies.

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

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

The description states a specific resource: an implied-volatility surface grid derived from a fetched options chain across several expirations. It is clearly distinct from siblings like track_gamma_squeeze_mechanics or mandelbrot_fractal_analysis, though it is phrased as a noun phrase rather than an action verb, so what the tool *does* 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 call this versus the other analytics tools, no prerequisites (does it need a live market session or a subscribed options feed?), and no stated exclusions. The agent must infer usage entirely from the description's subject matter.

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