NORTH7 Finance Trading Signals & Stock Market Intelligence

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

With no annotations present, the description carries the full burden, and it does disclose real operational traits: output format (JSON), auth requirement ('FREE - no API key needed'), and cost (free). It does not cover data freshness/latency, rate limits, or failure behavior, which are the remaining gaps for an unannotated aggregator endpoint.

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-loaded with the primary value proposition, then the payload contents, then two short qualifier fragments for format and cost. The field enumeration is long but each item maps to distinct returned data, so little waste; the trailing 'JSON format. FREE' fragments are slightly clipped rather than smoothly integrated.

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 describe returns — and it does, itemizing every major field including enum-like ranges (risk 0-100, BULL/BEAR/SIDEWAYS/CRISIS, DEFENSIVE/CAUTIOUS/FAVORABLE). For a zero-parameter, unannotated read tool this is close to sufficient; only refresh cadence and error behavior 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 per the baseline this scores 4. The description correctly implies a single no-argument call returning a full package, with nothing parameter-shaped to mislead the agent.

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 — returns a complete market context package — and then enumerates exactly what is inside (risk level, crises, regime with VIX, guidance, hot regions, data summary, next calls). The 'all in one call' framing plus 'recommended FIRST tool' distinguishes it from single-purpose siblings such as get_market_regime and get_risk_index without needing to open either schema.

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

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

Explicitly tells the agent when to reach for it: 'the recommended FIRST tool for any market-monitoring agent.' That is clear situational guidance. It stops short of naming the alternatives (e.g. use get_market_regime for a regime-only probe) or stating when not to use it, so it is clear context rather than a full routing rule.

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

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

With no annotations, the description carries the full burden and does reasonably well: it discloses freshness (daily update), cost (2 credits per call), response format (JSON), and the substance of each record (risk score, alerts, directional assessment, seasonal pattern, AI reasoning). It omits any statement of read-only safety, auth requirements, or rate limits beyond cost, so it is strong but not complete.

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-loaded with the return content and payload size, with cost and freshness trailing. The 15-item commodity enumeration is long but functions as a genuine scope boundary. Slightly dense as a single run of sentences, but 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?

There is no output schema and no annotations, so the description must describe the return payload itself, which it does: score range, alert type, directional call, seasonal patterns, AI reasoning. Freshness and cost are covered. Missing coverage is minor: no geographic/exchange scope, and no note on whether the payload is a single object or per-commodity list.

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, which sets the baseline at 4. There is nothing for the description to clarify on the input side, and it correctly spends no words on parameters.

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

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

Specific verb ('Returns') plus a precisely bounded resource: risk scores 0-100 and disruption alerts, with the exact 15 commodities enumerated. That scope statement lets an agent tell it apart from get_prices or get_trading_signals by content. It falls short of 5 only because it never name-checks a sibling tool to route the agent 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?

No when-to-use guidance and no named alternative among the twelve siblings, so the agent must infer usage from the resource name. The 'Updated daily' and 'Costs 2 credits per call' notes are decision-relevant constraints that partially compensate, giving implied rather than explicit 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 full burden of behavioral disclosure. It mentions that events are sorted by impact score descending, that the tool is free with no API key, and that it returns structured data. While it doesn't cover rate limits or data freshness, the disclosed behaviors are relevant and helpful for an agent.

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 concise—two sentences plus an example—with the core purpose front-loaded. Every sentence contributes value: what it returns, how to use it, sorting behavior, cost/auth status, and a concrete example. 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?

Given the tool's simplicity (two optional parameters, no output schema, no annotations), the description is complete. It covers the data returned, sorting order, filtering logic, and authentication requirements. An agent has all the information needed to call it correctly and interpret results.

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 meaning beyond the schema by clarifying that min_impact defaults to 0 (all events), recommending 7+ for high-impact only, and explaining the region filter implicitly through the list of regions in the schema. The example ties both parameters together, adding practical 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 clearly states the tool's purpose: 'Get structured geopolitical and market events with impact scores' and enumerates the fields returned (headline, impact_score, affected sectors, etc.). It distinguishes itself from sibling tools like get_impact or get_risk_index by focusing on events with impact scores, and the example further clarifies its behavior.

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 provides explicit usage guidance: 'Use this to detect market-moving events and filter by minimum impact or region.' It also gives an example (min_impact=7) that illustrates how to apply filters. However, it does not explicitly state when not to use this tool or mention alternative tools for different scenarios, so it loses a point.

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, so the description carries the full burden. It discloses the return shape (directional assessment, confidence, driver explanation, timeframe), the cost model ('FREE — no API key needed'), and the upstream data sources. However it does not state whether this is read-only in effect, whether results are cached/real-time, or how stale the event data may be.

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-loaded with the core purpose and return contents in the opening sentences. Most sentences earn their place, though 'JSON format. FREE — no API key needed.' is slightly promotional filler.

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

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

With no output schema, the description must explain returns and it does so adequately (direction, confidence, driver, timeframe). For a zero-required-param read tool this is close to complete; only the freshness/update semantics are 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 coverage is 100% and the single parameter is fully documented there, including 'Omit for all impacts'. The description's 'filter by specific asset to see all factors affecting it' adds only marginal meaning over the schema. Baseline 3 applies when the schema does the heavy lifting.

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: 'Map geopolitical events and crises to specific asset impacts', plus what it returns. An agent can tell it apart from most siblings, though 'combines crisis analysis, news data, alpha screening, and commodity scoring' overlaps with get_commodity_signals and get_trading_signals without explicitly drawing 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?

Offers implied usage ('Filter by specific asset to see all factors affecting it') but never says when to pick this over get_intelligence_briefing, get_commodity_signals, or get_events. No explicit when/when-not or prerequisites.

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 well: it discloses the credit cost (10 per call), the daily generation cadence, the 40+ source pipeline, and the structure of each event. It omits auth/permission requirements and any rate limits, leaving a few gaps for a paid tool.

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 front-loaded sentences that describe output, generation, language, and cost with little waste. Slightly dense but every sentence adds decision-relevant information.

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

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

With no output schema, the description usefully describes the return shape (impact score 1-10, affected sectors/assets, actionable implications) and the language parameter. It is complete enough to invoke correctly, though permission requirements for a credit-consuming call 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?

Schema description coverage is 100% and the single 'lang' parameter already documents 'en' default and 'de' with an enum. The description repeats the same language options without adding syntax or fallback behavior, so the baseline of 3 applies.

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

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

The description states a specific verb ('Returns') and a concrete resource (AI-generated geopolitical intelligence briefing with risk assessments across six named domains). It is readily distinguishable from siblings like get_events or get_risk_index by content, though it does not explicitly name or contrast those alternatives.

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 context is only implied: the daily generation cadence and 10-credit cost give the agent decision signals, but there is no explicit when-to-use, when-not-to-use, or named alternative among the many sibling intelligence tools. The agent must infer the scenario itself.

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 and largely does: it discloses the update cadence (every 30 minutes), the auth/cost profile (FREE, no API key), the deterministic classification thresholds, and the return fields. It does not cover rate limits or error behavior, but the operational profile is well conveyed.

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-loaded with the classification logic, then returns, then usage, then operational notes. Dense but every sentence (regime rules, return fields, sibling pairing, cadence, cost) carries 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?

No output schema exists, and the description compensates by listing the return fields (regime, confidence, MA comparison, VIX, duration). No annotations, but safety profile is trivial for a read-only detection tool. Nearly complete, missing only edge-case behavior when data is unavailable.

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

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

The tool takes zero parameters, so per the rubric baseline is 4. The description correctly adds nothing about inputs since there are none.

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 ('detect') plus resource ('current market regime') and enumerates the four possible outputs (BULL, BEAR, SIDEWAYS, CRISIS) with the quantitative rule for each. This distinguishes it clearly from siblings like get_risk_index or get_trading_signals.

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

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

Explicitly says 'Use alongside get_risk_index before trading decisions,' naming a sibling and the workflow context. It gives clear when-to-use guidance but no when-not-to-use or boundary conditions versus the other signal 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 the 10-credit cost, explicitly states it is a research portfolio and not investment advice, and describes the returned data. This is solid transparency for a read-only view tool, though it could mention whether any auth or rate limits apply.

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

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

The description is front-loaded with the main purpose, followed by concrete return details and the credit cost. Every sentence adds value; there is no filler or redundant restating of the tool name.

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

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

With no parameters and no output schema, the description fully equips an agent to call the tool correctly and interpret results: it lists active position fields, portfolio return, performance history, and the credit cost. The information provided is complete for a simple getter tool.

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

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

There are zero parameters, so the schema already provides full coverage. The description adds relevant context about what the portfolio represents and what metrics are returned, which is useful given the absence of an output 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 ('View') and specific resource ('current NORTH7 model portfolio positions and performance metrics'). Clearly distinguishes itself from sibling signal/analysis tools by focusing on the model portfolio rather than market signals or agent context.

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

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

Explicitly says when to use it: to see current positions, entry prices, P&L, and portfolio performance. It does not name alternatives or state when not to use it, but the purpose is clear enough that an agent can infer appropriate use versus the listed 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 and largely meets it: it discloses the data source (Yahoo Finance), freshness (updated every 2 minutes during market hours), and a quota cost (1 credit per call). It still omits return-format/pagination detail, but the operational traits an agent needs before calling are covered.

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 resource and coverage, then source, freshness, usage mode, and cost in tightly ordered sentences. Every sentence carries distinct information with no redundancy.

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

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

With no annotations and no output schema, the description compensates well: it enumerates the returned fields (price, daily change percentage, volume), the asset universe, freshness, and cost. An agent has enough to call correctly and anticipate results.

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% for the single symbols parameter, so the schema already documents format and the omit-for-all behavior. The description restates the comma-separated vs omit semantics without adding syntax or constraints beyond the schema, so the baseline 3 applies.

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

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

States a specific verb (Returns) and resource (real-time price, change, volume) with explicit asset coverage (80+ assets, US stocks, commodities, indices) and named data source. An agent can distinguish it from get_stock_analysis or get_commodity_signals, which imply deeper per-asset analysis rather than bulk price fetching.

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

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

Explicitly states both invocation modes: request specific comma-separated symbols, or omit for all 80+ assets. This is clear context for using the tool, but it names no alternative sibling tool or when-not-to-use condition (e.g. versus get_stock_analysis for deep dives).

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 return shape ('matched entities, connected nodes, and weighted edges with evidence') and the authentication requirement ('FREE — no API key needed'). It does not specify behavior when no parameters are provided, but otherwise is transparent.

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 sentences, each earning its place: what the tool queries, entity types, examples, and return format. It is front-loaded and free of filler.

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

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

For a two-parameter tool with no output schema, the description explains what is returned and how to query. It could be more complete by clarifying what happens when no entity or type is supplied, but overall 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?

Schema coverage is 100%, so the baseline is 3. The description adds meaningful value by giving concrete entity ID formats and examples for both parameters, which helps an agent populate them correctly.

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 a specific verb ('Query'), a resource ('the NORTH7 knowledge graph of entities and relationships'), and lists supported entity types. This makes it easy to distinguish from sibling market-data tools like get_prices or get_events.

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 concrete instructions and examples for using the entity parameter ('IR', 'CL=F', 'energy'), and implies this tool is for relationship-oriented queries. It does not explicitly name alternatives or state when not to use it, so it stops short of a 5.

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 and does disclose two useful traits: a 30-minute refresh cadence and that no API key is required ('FREE'). It implies a read operation via 'Returns' but never states read-only/exact behavior beyond that, so it falls short of 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?

Front-loaded with the core purpose, then the interpretation bands, regions, cadence, and cost. Dense but every sentence (bands, regions, refresh, free) adds actionable information; it is slightly run-on but not wasteful.

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

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

With no output schema, the description must explain the return shape, and it does cover the 0-100 scale, regime values, and per-region breakdown. The structure of the 'list of active geopolitical crises' is left unspecified, a minor gap for a zero-parameter tool.

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

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

The tool takes zero parameters, which is the baseline-4 case. The description's scoring bands (0-30=CALM ... 70-100=CRITICAL) describe output interpretation rather than inputs, so no parameter 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?

States a specific verb and resource ('Returns global market risk index 0-100') and enumerates the payload (geopolitical crises, market regime, per-region scores), so an agent knows exactly what it gets. The scoping is concrete enough to separate it from siblings like get_market_regime and get_commodity_signals.

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 never says when to reach for this tool versus get_market_regime, get_intelligence_briefing, or the sector/commodity siblings. It describes the payload but gives no usage context, triggers, or 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 provided, the description must carry the full behavioral burden. It discloses that data is updated daily and costs 2 credits per call, and describes the return content, but omits authentication needs, rate limits beyond credits, and error behavior. This partial disclosure merits a 3.

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

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

The description is front-loaded with the primary return value and structured logically. The parenthetical list of all 11 sectors is somewhat verbose but informative; overall the four sentences are efficient and earn their 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 no output schema and no annotations, the description explains the return values well (breadth score, rotation direction, leaders/laggards, momentum, advance/decline ratios) and adds operational context like daily updates and credit cost. It is nearly complete, missing only minor details like response format or authentication requirements.

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

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

There are zero parameters, so the baseline score is 4. The description does not need to add parameter meaning beyond what the empty schema provides.

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 verb ('Returns') and resource ('breadth score and rotation direction for all 11 US stock market sectors'), making the tool's output clear. However, it does not explicitly differentiate from siblings like get_market_regime or get_trading_signals, 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?

There is no guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. The cost and update frequency are not usage guidelines, just operational facts, similar to the MID calibration example where update_drive received a 2.

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 does disclose two valuable traits: the generator (Claude AI) and the per-call cost (5 credits) — the cost being genuinely important for an agent decision. However, it omits auth requirements, rate limits, latency, and caching behavior, leaving real gaps for a paid external analysis call.

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-loaded with the core verb and scope, then a dense enumeration of output categories. Every clause carries information; the parenthetical indicator list is long but earns its place. Slightly list-heavy but no filler 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 and no annotations, the description compensates by enumerating the returned analysis categories (fundamentals, technicals, sentiment, directional score with confidence), so the agent knows what comes back. Operational traits like cost and generator are covered. Remaining gaps are auth/rate-limit details.

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

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

Schema coverage is 100% and the single 'ticker' parameter already documents format and examples ('AAPL', 'MSFT'). The description only restates that ticker is required and that US tickers are in scope, adding no syntax or validation detail beyond the schema. Baseline 3 is correct when the schema does the heavy lifting.

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 ('Returns comprehensive AI analysis for any US stock ticker') and enumerates the exact output categories: fundamentals, technicals, sentiment, and directional assessment. It is clearly distinguishable from pipeline siblings like get_prices or get_trading_signals by the comprehensiveness/AI-analysis framing, though it never names a sibling 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?

No when-to-use or when-not-to-use guidance. It notes 'Ticker parameter required' and 'Costs 5 credits per call', which is helpful operational context, but nothing tells the agent when to prefer this over get_trading_signals or get_prices. Usage 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?

With no annotations, the description carries the full burden and does well: it discloses update cadence ('Updated daily'), response format (JSON), and cost ('Costs 1 credit per call') — an economically important trait rarely stated. It omits auth/subscription requirements and rate-limit behavior, so it's strong but not complete.

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 front-loaded with the returned fields, then sources, then filtering, then cadence/cost/format — a logical progression. It runs somewhat long because the five source descriptions are duplicated from the schema, which is redundant but not wasteful enough to hurt readability.

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

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

Despite the absence of annotations and an output schema, the description compensates by enumerating return fields, format, cadence, and cost, which is what an agent needs to decide and call. The main residual gap is permissions/authorization context, which is not addressed.

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 enum parameter is fully documented there, so the baseline is 3. The description essentially restates the same source labels and meanings verbatim rather than adding syntax, defaults, or combination rules beyond what the schema already provides.

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

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

The description opens with a specific verb and resource ('Returns today's AI-generated market data points for equities') and enumerates the returned fields, so the tool's function is unmistakable. The 'for equities' scope implicitly separates it from get_commodity_signals, but no sibling is named explicitly, so it falls short of the top tier.

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 explains how to use the source filter ('Filter by source or omit to receive all data points combined'), which is genuine usage guidance. However, it never states when to prefer this tool over get_stock_analysis, get_commodity_signals, or get_sector_radar, leaving the selection decision to inference.

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