Seiche — funding-stress terminal

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

Annotations already indicate a read-only, idempotent, non-destructive operation. The description adds behavioral context by explaining how the tool replays episodes point-in-time and how it distinguishes transmission (external wrecks) from 'staying quiet' (crypto-native wrecks). This goes beyond annotations and gives agents a sense of the expected output behavior.

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

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

The description is concise and well-structured: it opens with the core concept, gives concrete examples, explains the semantic distinction, and closes with a clear use case. Every sentence adds value, with no redundancy or filler.

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

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

For a read-only record tool with no parameters and no output schema, the description is largely complete. It conveys the domain, the point-in-time replay approach, and the interpretative value (transmission vs. quiet board). It stops short of detailing data fields or return format, but this is acceptable given the tool's nature and strong annotations.

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

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

The tool has zero parameters, so the schema is trivially complete. The description provides no parameter-specific details because none are needed. Per the rubric, a zero-parameter tool receives a baseline of 4, which is appropriate here.

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

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

The description clearly identifies the tool as a historical record of crypto stress episodes replayed against the dollar-funding board. It names specific episodes (Black Thursday, Terra, FTX, etc.) and explains the two categories (external vs crypto-native wrecks), making the tool's purpose unambiguous and distinct from siblings like funding_stress_now or replay_asof.

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 states the intended use: 'Use for any does TradFi funding stress reach crypto question, grounded in the record.' It implies this is for historical analysis rather than forecasting, but does not explicitly name alternative tools or exclusion criteria. The guidance is clear but not exhaustive.

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 read-only, idempotent, non-destructive behavior. The description adds meaningful context by listing the specific data sources and the concept of 'fault status', which goes beyond the structured hints. It does not contradict annotations and lets the agent know the scope of the health check.

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

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

Two short sentences: the first states the tool's function and scope, the second gives a direct usage instruction. Every word earns its place, and the description is front-loaded with the most important 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?

For a simple no-parameter tool with no output schema, the description provides enough detail about what it does and when to use it. It could perhaps specify the format of the output or what 'fault status' means, but the core purpose and context are sufficiently clear for an agent to select and invoke the tool correctly.

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

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

The tool has zero parameters and the schema is empty, so the baseline of 4 applies. The description does not need to explain parameters, and it provides context about what the tool inspects (all underlying series) without needing to mention inputs.

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

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

The description clearly identifies the tool as reporting freshness, provenance, and fault status for underlying data series. It names specific sources (FRED, NY Fed, OFR, Treasury) and provides a distinct purpose: confirming the board is current before relying on a reading. This differentiates it from sibling tools that focus on stress forecasts or historical analogs.

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 instruction 'Call this to confirm the board is current before relying on a reading' gives a clear, actionable use case and timing. It does not explicitly mention alternatives but the context is sufficient for an agent to know when to invoke this tool versus others.

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 mark the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral context by enumerating the output components and mentioning data fault reporting. It does not contradict any 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 two sentences: the first covers purpose and output components, the second gives usage guidance. It is concise, front-loaded, and contains no redundant 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?

For a zero-parameter, well-annotated snapshot tool, the description fully covers what it returns, when to use it, and any caveats (data faults). It is complete for its complexity.

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

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

The tool has zero parameters, so the baseline is 4. The description effectively describes what the tool returns, which is more than necessary since there are no parameter semantics to clarify.

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: a live money-market funding-stress reading with specific output components (0-100 index, regime, decomposition, tell, faults). It distinguishes itself from the forecast sibling by emphasizing 'live' and 'current'.

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 usage guidance: 'Ask this whenever an analysis touches US dollar funding, repo, reserves, the Fed's balance sheet, or liquidity conditions.' This clearly defines when to use, but doesn't explicitly mention when not to use or alternative 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context beyond these: it explains that the tool returns a frequency of stress events and a novelty flag based on historical similarity. This enriches the agent's understanding of the tool's output and logic.

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

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

The description is two sentences that pack all essential information: what the tool returns, how it works (historical analogy), and when to use it. There is no wasted wording, and the key return values are 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, the description must explain return values, and it does: similar days, frequency of stress events, and novelty flag. It also covers usage guidance. Given the tool's simplicity and the presence of supporting annotations, the description is fully complete.

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

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

The tool has zero parameters and an empty schema, so the schema provides no parameter details. The description compensates by clarifying the implicit inputs (today's funding conditions) and the output semantics. This meets the baseline for 0-parameter tools.

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 what the tool does: it identifies historical days most similar to today's funding conditions and reports how often those analogs led to a stress event, plus a novelty flag. This specific verb+resource structure distinguishes it from sibling tools like funding_stress_forecast or funding_stress_now.

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 context: 'Use to ground a “what usually happens from here” question in real history.' This tells the agent when to use this tool, though it does not name specific alternative tools or exclusions. The clear context earns a 4.

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 this as read-only, idempotent, and non-destructive. The description adds valuable behavioral context: weekly cadence, point-in-time data, composition from public sources, and a funding-fragility flag. It does not contradict annotations and provides transparency about data frequency and sourcing beyond the safety 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 approximately 70 words and front-loads the core purpose in the first sentence, followed by a list of components and usage guidance. It is slightly dense but each phrase adds meaningful detail; no fluff or redundancy. The final sentence about free public data is minor but acceptable.

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, the description sufficiently covers what data is included, the cadence, and the point-in-time nature. It does not describe the exact output format (e.g., numbers vs. prose), but for a parameterless tool with this level of component detail, it is complete enough for an agent to understand expectations.

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

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

The tool has zero parameters, so the baseline is 4. The description does not need to elaborate on parameter meaning since none exist. It instead offers context about the data sources and indicators, which indirectly informs what the tool returns.

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 is a positioning nowcast for hedge funds, pensions, and sovereigns, listing specific components like CFTC leveraged-fund net short and foreign-official custody flows. This distinguishes it from siblings such as funding_stress_now or positioning_book by specifying exact indicators and asset classes covered.

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 provides usage guidance: 'Ask this when a question involves hedge fund leverage, the basis trade, pension duration bids, or sovereigns buying/selling Treasuries.' It does not mention when not to use or name alternatives, so it lacks the full when/when-not/alternatives structure for a 5, but the provided direction is clear and actionable.

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 goes beyond the annotations (readOnly, idempotent, non-destructive) by specifying the exact content of the report: confidence intervals, an orthogonal robustness test, named episodes with hits/misses, and caveats. This informs the agent what to expect and signals that the tool provides a candid assessment. It does not contradict 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 compact yet informative, listing key components in a single flowing sentence and closing with a clear usage statement. It is front-loaded with the resource name and avoids redundancy with annotations or schema.

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

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

Given the tool has no parameters and no output schema, the description must carry the full documentation burden. It enumerates the returned elements (recall/precision CI, robustness test, episodes, caveats) and explains the intent, providing enough context for an agent to invoke it appropriately. There's no ambiguity about what the tool will return or when to use 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?

The input schema has zero parameters, so there are no parameter semantics to clarify. The description's mention of 'labelled funding events' provides a conceptual anchor but doesn't need to explain any schema fields. Baseline of 4 is appropriate for no-parameter tools.

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

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

The description clearly identifies the tool as a 'backtest scoreboard' containing recall/precision with confidence intervals, robustness test, episode list, and caveats. This distinguishes it from siblings like funding_stress_forecast or historical_analogs by focusing on honest track-record evaluation. The specific domain of 'labelled funding events' anchors its scope.

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?

'Use to judge how much to trust the readings' provides an explicit, actionable context for when to invoke this tool. It implies the tool is for evaluating the reliability of predictions against historical labeled events, a distinct use case from live stress tests or desk briefs. However, it doesn't name alternative tools for comparison, so only a slight deduction.

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