patternfetch

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

Annotations already include readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds behavioral context: 'NOT a prediction, NOT a backtest', 'past distribution does not guarantee future results', and clarifies it returns a distribution, not a point estimate. These go beyond annotations and set proper expectations.

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 well-structured with clear sections (parameters, when/when not, examples, caveats). Every sentence serves a purpose, and it is concise given the complexity.

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

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

For a tool with 5 parameters, no output schema, the description covers the function, parameter details, usage context, and important caveats. It is fully self-contained and leaves no ambiguity.

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

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

With 100% schema coverage, the description still adds value by explaining default values for window and horizon, detailing how market is inferred from ticker, and warning about ticker behavior (crypto vs ETF). This provides meaning beyond the 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 clearly states the tool's purpose: find historical windows matching current price action and return a full distribution of outcomes. It specifies the resource ('same series'), action ('find and return distribution'), and distinguishes from siblings by emphasizing 'FULL distribution' and 'IN THE SAME SERIES'.

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 when to use ('want the historical spread of outcomes') and when not ('want current technical picture' → use brief; 'find candidates across market' → use scan; 'need one expected value'). Provides clear alternative tool names.

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

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

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds crucial context: coverage of US stocks/ETFs (split/dividend adjusted, delayed/EOD) and crypto spot (realtime), plus ticker ambiguity warning. No contradictions.

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?

Description is well-structured with clear sections and examples, but slightly lengthy. Every sentence provides value; formatting improves 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 no output schema, the description thoroughly explains what the tool returns (patterns with confidence, backtested base rates, support/resistance, trend/regime, indicators, one-line summary). It covers asset class differences and token-saving rationale, making it complete for an AI 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?

Schema coverage is 100%, and the description adds significant meaning beyond the schema: for ticker (crypto pair vs stock ETF, notice field), timeframe (coverage differs per asset class, see capabilities tool), market (optional override), limit (fewer bars = fewer tokens).

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 a token-compact market-state brief for a stock, ETF, or crypto ticker + timeframe.' It lists specific outputs (candles, patterns, support/resistance, etc.) and distinguishes from siblings by focusing on a single ticker with compact summary.

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?

Explicit 'WHEN' and 'WHEN NOT' conditions are provided: use when needing technical picture without raw data, avoid for order execution or portfolio advice. Examples for ticker and timeframe are given, aiding correct invocation.

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 signal read-only, idempotent, non-destructive behavior. The description adds significant context: it takes no arguments, returns static self-description on every call, and explicitly states it contains no market data. There is 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 well-structured with a clear listing of what is returned and separate WHEN/WHEN NOT sections. It is slightly verbose but every sentence adds value, and critical information is front-loaded.

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

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

For a zero-parameter tool with no output schema and rich annotations, the description is fully complete. It explains the return content, use cases, and what the tool does not provide, ensuring the agent can use it correctly without additional 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?

There are zero parameters, so the baseline is 4. The description confirms 'Takes no arguments', which is sufficient. No additional parameter details are 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 uses a specific verb 'Return' and clearly defines the resource 'patternfetch's own capability matrix'. It enumerates exactly what the matrix contains (asset classes, data sources, timeframes, etc.) and explicitly distinguishes it from sibling tools by stating it contains NO 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?

The description provides explicit WHEN and WHEN NOT sections: use it at session start to learn supported features, and avoid it if you already know the ticker/timeframe support or need actual market data. This effectively guides the agent on when to call this tool versus its 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?

Description adds context beyond annotations: it specifies that the tool returns changed=false when nothing material changed, and states 'Impersonal data, not advice,' reinforcing the read-only nature. This aligns with readOnlyHint=true and no destructive 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?

Description is extremely concise: one sentence for purpose, then WHEN/WHEN NOT, return value note, example, and final disclaimer. Every sentence earns its place, well-structured and front-loaded.

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

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

Given the tool has 4 parameters and no output schema, the description covers the key behavioral aspects: what changes are detected, return value indication, and usage context. Could be slightly more detailed on output structure, but sufficient for an 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?

Schema coverage is 100%, so schema already documents parameters. Description adds minor value (e.g., 'Fewer bars = fewer tokens' for limit, example for ticker/timeframe) but does not significantly enhance understanding beyond 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?

Description clearly states the tool gets only what changed since the last brief for a ticker+timeframe, listing specific change types (trend flips, new patterns, RSI-state changes). It explicitly distinguishes from sibling patternfetch_brief by stating when to use each.

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

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

Provides explicit WHEN (agent polls same market repeatedly and wants minimal tokens) and WHEN NOT (first look at a market, use brief) conditions. Includes an example JSON and notes that return value indicates if anything changed.

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

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

Annotations already indicate readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds that the alignment/divergence is 'impersonal DESCRIPTIVE data, not a signal to act on' and includes 'Not investment advice.' This provides additional behavioral context beyond the 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 well-structured with clear sections (WHEN, WHEN NOT) and includes an example. While it is a bit lengthy, every sentence serves a purpose. Minor redundancy could be trimmed, but overall it is efficient.

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

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

Given the tool has 4 parameters, no output schema, and moderate complexity, the description is thorough. It explains the return content (briefs per timeframe plus alignment read), provides defaults, constraints (max 4 timeframes), and handles edge cases (crypto vs ETF). This enables an agent to use the tool correctly without additional assumptions.

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%. The description adds valuable information beyond the schema: it clarifies that bare crypto symbols like 'BTC' are treated as US-listed ETFs and that a 'notice' field is included in such cases. It also specifies default timeframes and that at most 4 timeframes are allowed.

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 verb 'Get' and the resource 'multi-timeframe market-state view'. It specifies that the result includes a brief for each requested timeframe and a cross-timeframe alignment read. It distinguishes itself from siblings by noting that it avoids making three separate brief calls.

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

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

The description explicitly includes WHEN and WHEN NOT sections. WHEN states: 'an agent wants to know if a setup is confirmed across horizons or conflicting between them, without making 3 separate brief calls.' WHEN NOT states: 'you only care about one timeframe (use brief).' This provides clear guidance and names the alternative sibling tool.

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

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

Annotations already indicate safe, idempotent read operation. The description goes beyond by stating it is precomputed daily over a curated universe, fast and cheap, and provides impersonal historical data not investment advice. 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 well-structured with bolded terms, clear sections, and efficient use of sentences. Every sentence provides unique value, and the example input helps understanding. Length is appropriate for the tool's complexity.

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 no output schema, the description thoroughly explains the output fields (sym, tf, baseRate, ci95, etc.) and their interpretation, including the drift-free comparison fields. Context signals (0 required params, 7 optional) are well 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 coverage is 100%, but the description adds significant value for each parameter, especially minLift and minBaseRate, explaining their interpretation, caveats, and preference. It clarifies the ranking order and output field 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 clearly states the tool scans US stocks, ETFs, and crypto for tickers in a given regime or showing a pattern, ranked by backtested base rate. It explicitly distinguishes from siblings like brief (for known tickers) and provides a concrete example query.

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 includes explicit 'WHEN' and 'WHEN NOT' sections, directing agents to use brief for known tickers and to prefer minLift over minBaseRate. It also explains when minBaseRate is misleading.

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