quant

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

Annotations already declare readOnlyHint=true, so the description adds value by disclosing the output (gap, signal, sample-size quality) and the two input modes. 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?

The description is two sentences plus a list of IDs, reasonably concise. It could be more structured with bullet points for the ID list, but it's efficient 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 3 parameters and no output schema, the description explains the return values (gap, signal, quality) and covers both input modes. It is complete for the tool's 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?

Schema coverage is 100% with descriptions for all parameters. The description repeats the choice between baseRateId and baseRateValue but adds little new meaning beyond the schema. Baseline 3 is appropriate.

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 compares a market price against a historical base rate and computes gap, signal, and sample-size quality. It lists specific use cases and IDs, distinguishing it from sibling tools like bayes_update or calculate_ev.

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 says to pass either a known baseRateId or a custom baseRateValue, and provides example queries like 'how does this price compare to history'. It could be improved by noting when not to use it, but the guidance is clear.

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

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

Annotations declare readOnlyHint=true, and the description does not contradict this. The description adds that the tool 'returns the posterior probability and the per-step chain,' which is a helpful behavioral detail beyond the annotations. However, it does not disclose assumptions like independence of evidence.

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 three sentences: first explains the operation, second specifies input/output, third lists example intents. It is front-loaded and contains no unnecessary words.

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

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

Without an output schema, the description covers the return values ('posterior probability and per-step chain'). It also explains the required inputs (prior and evidence with likelihoods). It could mention assumptions like evidence independence for full completeness.

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%, with all parameters described. The description does not add significant new information about parameters beyond what the schema provides, so it meets the baseline of 3.

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 specific verb and resource: 'Update a prior probability with one or more pieces of evidence using Bayes theorem.' It also provides example user intents like 'update my estimate with new information' and 'posterior probability,' which clearly distinguish this tool from siblings like 'convert_probability' or 'kelly_size.'

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

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

The description gives explicit usage examples like 'Use for "update my estimate with new information"' and 'how does this news change the odds.' It does not explicitly state when not to use it or mention alternatives, but the examples strongly imply the intended 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?

The description aligns with annotations (readOnlyHint=true) by presenting it as a calculation. It adds value by detailing the output (% edge and BUY/SELL/SKIP signal) beyond what annotations provide. Could mention assumptions like binary resolution.

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 three sentences, each carrying essential information: what it does, input explanation, and use cases. No redundant text; front-loaded with the core 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?

For a simple calculation tool with no output schema, the description adequately explains returns (percentage edge and signal). Could specify output format more precisely, but it's 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 description coverage is 100%, so the schema already fully explains the parameters. The description does not add new information about parameters beyond what's in the schema, which is acceptable but not additional 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 calculates the expected-value edge for prediction-market contracts, specifying the markets (Kalshi/Polymarket). It distinguishes from siblings like 'bayes_update' or 'scan_mispricings' by focusing on single-contract EV with a clear BUY/SELL/SKIP signal.

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 use cases ('is this contract mispriced', 'what is my edge', 'should I take this position'), guiding when to use. It does not mention alternatives or when not to use, but the context is clear.

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

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

Annotations already indicate readOnlyHint=true (no side effects) and openWorldHint=false. The description adds behavioral context: it requires a 'correlation-aware estimate' and returns a specific set of outputs including a verdict tier. No contradictions, and it enhances understanding 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?

Two sentences efficiently convey the tool's purpose, inputs, outputs, and use cases with no unnecessary words. Information density is high.

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 only two simple parameters and no output schema, the description completely covers what the agent needs to know: how to invoke it (provide legPrices and trueWinProbability) and what it returns (EV%, odds, trap flag, verdict). No missing 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% with clear descriptions for both parameters. The description mentions 'correlation-aware estimate' for trueWinProbability, but does not significantly add new semantics beyond the schema. Baseline of 3 is appropriate.

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 grades a 'same-game combo (parlay-style multi-leg position)' and lists all outputs (EV%, fair odds, trap flag, verdict). It distinctively targets this specific use case, separating it from sibling tools like calculate_ev or commodity_edge.

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 use-case phrases like 'is this combo worth it', 'grade my parlay', and 'same-game combo value' are provided. However, there is no explicit mention of when not to use this tool or how to choose among sibling tools, though the domain is clear.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, indicating a safe read operation. The description adds value by detailing the output fields (entry side/price, resolve criterion, model probability, edge, confidence tier, quarter-Kelly sizing) and the Pro key prerequisite. 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?

The description is well-structured with a clear purpose statement, followed by output details and example queries. It is slightly verbose but front-loaded appropriately. Could be more concise without losing clarity.

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 a single required parameter, full schema coverage, and no output schema, the description adequately explains what the tool returns and prerequisites. It addresses the core need for a specific trade signal.

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% with a well-described enum parameter. The description echoes 'silver or bitcoin' but does not add significant meaning beyond the schema's description. Baseline score of 3 is appropriate.

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 it returns today's highest-conviction silver or bitcoin trade signal from the PMP edge model, specifying output elements and the commodity parameter. However, it does not explicitly differentiate from sibling tools like 'combo_edge' or 'market_pulse'.

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 examples ('silver edge today', 'bitcoin trade signal', 'is there a commodity edge') and mentions the Pro key requirement. However, it lacks guidance on when not to use or comparison to alternatives.

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, so the tool is known to be non-destructive. The description adds that it returns all three formats and specifies American odds formatting. However, it does not disclose constraints like valid ranges (e.g., probability 0-100) or behavior on invalid inputs, which would enhance transparency.

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 states the core action, the second provides examples and a formatting rule. It is front-loaded, no redundant words, and every sentence adds value. Ideal for quick comprehension.

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

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

For a simple conversion tool with 2 parameters and no output schema, the description covers the main functionality and a formatting detail. It lacks edge case or error handling info, but this is a minor gap given the tool's simplicity and the presence of sibling tools that handle more complex scenarios.

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% with both parameters documented. The description adds context that only one format should be provided and all three are returned, but does not significantly enhance understanding beyond the schema. Baseline 3 is appropriate.

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 converting between three specific formats: implied probability, American odds, and decimal odds. The examples ('what is +150 as a probability') illustrate the purpose well. It is distinct from sibling tools which involve betting calculations or market analysis, not simple format conversion.

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 examples and a formatting note (no commas in American odds). It states 'Give one value and its format and get all three back', guiding the user on input and output. While it doesn't mention when not to use it or alternative tools, the context of sibling tools and the clear conversion focus make this sufficient.

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 and openWorldHint; the description adds the requirement for a Pro key and describes the output format, providing useful behavioral context beyond 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 concise, front-loaded, and contains no redundant information; every sentence serves a purpose.

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 lacking an output schema, the description adequately explains the return values (gap, signal, cheaper venue) and prerequisites, making it sufficiently complete for a simple 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 input schema has full description coverage for its single parameter, minGap, so the description adds no additional value beyond what the schema provides, meeting the 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?

The description clearly states the tool scans for cross-platform price gaps between Kalshi and Polymarket on sports contracts, using specific verbs and distinguishing it from sibling tools like scan_mispricings.

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 clear usage context with example queries and a prerequisite ('Pro key required'), but does not explicitly exclude alternative tools or scenarios.

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, so the description's statement 'Compute' is consistent and adds no new behavioral insight beyond confirming it returns 'dollar stake and a risk rating'. The description does not disclose additional traits like side effects or authorization needs.

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 four sentences with no waste. It front-loads the purpose, lists inputs and outputs, and includes usage examples—all succinctly.

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 computation tool with no output schema, the description covers everything: what it does, what inputs it takes, and what it returns ('dollar stake and a risk rating'). It is fully sufficient for an agent to invoke correctly.

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

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

Schema description coverage is 100%, so baseline is 3. The description summarizes the parameters but does not add new meaning beyond what the input schema already provides for each parameter.

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

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

The description clearly states the tool computes optimal Kelly position size for prediction-market contracts. It provides specific inputs and outputs, and includes example queries that distinguish it from sibling tools like calculate_ev or bayes_update.

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 says 'Use for "how much should I stake", "what is my position size", "Kelly sizing for this trade".' This gives clear usage context but does not explicitly exclude alternatives or mention when not to use it.

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

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

Annotations already provide readOnlyHint=true and openWorldHint=true. The description adds behavioral context: it reads a daily composite, requires a Pro key, and returns the composite plus six categories. 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?

Two concise sentences, front-loaded with the main purpose, then details on output and usage. Every sentence adds value with no fluff.

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?

Even without output schema, the description covers key return values (composite, regime, six category scores) and usage context. Minor omission of error scenarios, but adequate for a simple read 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?

No parameters in input schema, schema description coverage 100%. Baseline 4 applies as the description does not need to add parameter info. Description is sufficient.

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

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

The description uses specific verb 'Get' and clearly identifies the resource: 'US macro-health composite (0–100) and regime, plus the six category scores'. It distinguishes itself from sibling tools which are unrelated (e.g., bayes_update, kelly_size).

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 use cases: 'Use for "how is the US economy", "macro regime", "risk-on or risk-off"' and mentions prerequisite 'Pro key required'. Lacks explicit when-not-to-use or alternatives, but context is clear.

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

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

Annotations already set readOnlyHint and openWorldHint to true. The description adds value by detailing the output (markets, direction, edge, quarter-Kelly sizing, sorted by absolute edge) and confirms it is a read-only scan. No contradictions or missing behavioral cues.

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 (three sentences), front-loaded with purpose, and contains only essential information. No wasted words, and it efficiently covers key aspects: what, how, output, and prerequisites.

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 (2 optional parameters, no output schema), the description is complete: it explains the output format, prerequisite (pro key), and typical use cases. No gaps remain for an agent to correctly invoke the 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?

Schema coverage is 100%, so parameters are fully described in the schema. The description does not add new semantic details beyond what the schema provides, but it does mention sorting by absolute edge, which indirectly relates to parameters. Baseline score of 3 is appropriate.

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 'Scan' and the resource 'Polymarket contracts for mispricings against the PMP model'. It distinguishes itself from siblings by specifying the PMP model and providing use case examples like 'where is the edge today', making it unique among similar tools.

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

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

The description explicitly states 'Pro key required' and gives common usage phrases ('where is the edge today', 'mispriced markets', 'what should I trade'). It lacks explicit exclusion of when not to use, but the context is clear enough for an agent to infer appropriate scenarios.

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