PRUVIQ strategy verdicts (read-only)

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive behavior, so the trailing 'Read-only' adds little. The genuinely useful disclosure is that cells below the minimum sample are flagged, which tells the agent to expect sparse/low-confidence results; beyond that, nothing about data freshness or failure modes is added.

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

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

One dense sentence front-loads the resource and metric list, and the trailing 'Read-only' is short. The only waste is the redundant read-only restatement of the annotation, but the whole description is proportionate to the tool.

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?

An output schema exists, so return-value details are correctly omitted, and the description still previews the metrics and the minimum-sample flagging. For a single-parameter read tool this is nearly complete, missing only a pointer to sibling tools for verdict/ranking 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?

Schema coverage is 100% and the single parameter's description already lists the accepted symbol formats ('BTC, BTCUSDT, BTC-USDT-SWAP'). The description repeats those exact examples without adding format rules, normalization behavior, or case sensitivity, so it earns only the baseline 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 gives a specific verb ('Get'), a specific resource ('per-strategy backtest statistics'), and enumerates the metrics returned (trades, win rate, profit factor, total return, exit reasons, data window), scoped to one coin. It is clear what the tool does, though it never distinguishes itself from the potentially overlapping sibling get_strategy_verdict.

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

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

There is no explicit when-to-use or when-not-to-use guidance and no mention of alternatives. The inclusion of example symbols implies how to call it, but not when to prefer it over siblings like get_strategy_verdict or get_strategy_verdict/list_strategies.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so 'Read-only' in the description is largely redundant. What the description does add beyond structured fields is substantive: the interpretive caveat that a rank is not a verification, and the disclosure that entries carry a research status and low-sample flag worth scrutinizing.

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 purpose is front-loaded in the first clause, followed by the field inventory and then two short qualifying sentences. It is dense but every clause carries content (window scope, flags, the rank-vs-verification caveat); 'Read-only' is the one redundant fragment already covered by annotations.

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?

An output schema exists and the tool takes no parameters, so the description only needs to frame what the returned ranking means and how to interpret it. It does this, including the crucial 'rank is not verification' framing and the low-sample flag, leaving nothing an agent needs missing before calling it.

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

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

Zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly avoids inventing parameter-like details for a no-argument tool.

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 (get) and resource (PRUVIQ's published daily ranking snapshot), then enumerates the contents: best/worst strategy configurations by backtest over the published window, research status, sample size, low-sample flag, and headline note. This is enough for an agent to distinguish it from siblings like get_coin_strategy_stats or get_forward_verification_records.

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

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

Usage is implied rather than stated: 'daily ranking snapshot' and 'published window' suggest when the data applies, and the caveat 'A rank is not a verification' implicitly routes verification questions to siblings like get_forward_verification_records or get_strategy_verdict. However, no alternative is named and no explicit when-to-use / when-not-to-use condition is given.

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

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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description's 'Read-only' is redundant. The description does add useful context about the verification program content (sha256, OpenTimestamps, bitcoin block heights), but it does not disclose behavioral traits such as permissions required or side effects 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 front-loaded with the verb and resource, and the detailed record list is compact. The trailing 'Read-only.' sentence duplicates the readOnlyHint annotation and slightly reduces conciseness.

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?

The description is largely complete for a zero-parameter, read-only getter with an output schema and rich annotations. It identifies the resource and its contents, but it lacks any routing guidance relative to sibling tools such as get_strategy_verdict.

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 the baseline score is 4 per the rubric. The schema and description are consistent, and 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 uses a specific verb ('Get') and a uniquely named resource ('forward (out-of-sample, real-time) verification program records'), then details the record contents including sha256, OpenTimestamps proof state, and verdict dates. It does not explicitly differentiate itself from siblings such as get_strategy_verdict, 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?

The description gives no when-to-use guidance, no conditions for selecting this tool over alternatives like get_strategy_verdict, and no exclusions. It only states what the tool returns.

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

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered; the description's trailing 'Read-only.' is largely redundant. However, the description does add real behavioral content by disclosing the scope of what is returned (the specific criteria, definitions, and version info) and that it includes reproducible re-verification steps and public tooling.

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

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

One dense, front-loaded sentence that names the verb and enumerates the covered topics, followed by a two-word safety tag. It is efficient, though the standalone 'Read-only.' earns little since the annotation already states readOnlyHint=true.

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 zero parameters and an output schema present, the description need not explain return values or inputs. It adequately frames this as a documentation/explainer tool, though it could note whether the methodology is versioned or how it relates to the verification tools the siblings expose.

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 there is nothing for the description to disambiguate; the baseline for a no-parameter tool applies. No parameter semantics are needed or missing.

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 (Explain) and resource (the PRUVIQ methodology), then enumerates exactly what is covered: ranking criteria, research status definitions, verification criteria version, and research-ledger arbiter and cost. This clearly separates it from the sibling tools, which all return data rather than documentation.

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 phrase 'give the exact steps and public tools to re-verify a claim yourself' implies the use case (auditing/verifying a claim), but there is no explicit when-to-use statement, no prerequisites, and no routing to alternatives such as get_strategy_verdict or get_forward_verification_records. Usage is inferable rather than stated.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the description's 'Read-only' adds nothing. It does add useful behavioral context about what the verdict contains (per-block scope, fees included, sample size, verification record), but omits anything on auth, rate limits, or staleness of the published verdict.

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?

Purpose is front-loaded, followed by a usage directive and a compact enumeration of returned content. The middle sentence is dense with parenthetical asides but every clause conveys payload information, so it earns its length without much waste.

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?

An output schema exists, so return-value explanation is largely redundant but harmless. Combined with annotations covering the safety profile and a single well-documented parameter, the description gives an agent everything needed to call it correctly; only the lack of alternative-tool routing keeps it from a 5.

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

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

Only one parameter, and the schema already documents it fully (pattern, example 'bb-squeeze-long', pointer to list_strategies) at 100% coverage. The description adds no further semantics, 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 and resource ('Get the published verdict for one strategy') and enumerates the payload contents (tone, reasons, metrics, measurement date, sample size, fees, verification record). This clearly separates it from siblings like get_coin_strategy_stats and get_forward_verification_records, which surface raw stats versus a synthesized verdict.

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 before acting on any backtest number' gives a concrete trigger condition for invoking the tool. It does not name exclusions or the alternative sibling to use when a verdict isn't needed, so it stops short of full when/when-not guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered; the description's 'Read-only' merely restates it. It does add genuinely useful interpretive context beyond annotations: the headline metrics are the original backtest and not re-measured, pointing the agent at each row's headline_scope before comparing numbers.

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 action and scope, then packed with the field enumeration and the provenance caveat in a single dense sentence. Slightly long but every clause carries information; the trailing 'Read-only' is the only redundant fragment.

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 an output schema present the description need not explain return shape, yet it usefully previews the row contents and flags the headline_scope caveat. Combined with annotations and a fully covered parameter, an agent has everything needed to call it correctly; only the lack of sibling routing leaves a small gap.

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

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

Schema coverage is 100% and the enum values are documented in the schema, so the description's 'Optional filter by status' adds no syntax or semantics beyond what is already structured. Baseline 3 is appropriate 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 (list) and resource (strategies published by PRUVIQ), and enumerates the fields returned including research status, verdict, headline metrics and record URL. Against get_* siblings it is clear this is the bulk-listing tool rather than a single-record fetch.

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

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

Usage is implied: it lists everything and offers an optional status filter, which contrasts naturally with the get_* siblings that fetch one record. However, no alternative is named and no when-not guidance is given, so the agent must infer the routing.

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