backtesting-arena

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

No annotations are present, so the description carries the full burden. It only mentions idempotency but does not disclose other behavioral traits such as side effects (e.g., notifications), permission requirements, or whether the operation is reversible.

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 (one sentence plus a tier tag) and front-loaded with the key action. While efficient, it could benefit from a slightly more structured format to improve 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?

Given the simplicity of the tool (2 params, no output schema, no annotations), the description is too sparse. It omits important details like return values, effect on other subscriptions, or error conditions, leaving the agent underinformed.

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 both parameters. The tool description adds no extra meaning beyond the schema, 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 clearly states the verb 'deactivates' and the resource 'subscription', and the idempotency property distinguishes it from other tools like arena_subscribe_*. It is specific and unambiguous.

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 guidance is provided on when to use this tool versus alternatives, prerequisites (e.g., active subscription needed), or when not to use it. The description is silent on usage 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?

With no annotations, the description fully bears the burden and discloses that the tool returns then deletes updates (marks as delivered), which is a destructive read. It could elaborate on rate limits or idempotency but covers the essential 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?

Three sentences are concise and front-loaded with the main action. The inclusion of '[API Pro tier]' is useful. However, some structure (e.g., separating return content) could improve 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?

The description explains the return payload (subscription_type, current/previous value, trigger context) and the polling intent. No output schema, but the description compensates well. Lacks details on response format or error handling.

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 baseline is 3. The description adds no extra meaning to the 'context' parameter, which is already well-documented in the schema. No additional parameter semantics provided.

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 returns undelivered updates and marks them as delivered, with a specific verb-resource combination. It distinguishes from sibling tools like arena_subscribe_* which set up updates, while this consumes them via polling.

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 advises 'Call regularly to consume the polling queue,' providing clear usage context. However, it does not explicitly state when not to use or mention alternatives among siblings, though the polling nature is implied.

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 that execution is sequential and slow (10-50s) and mentions quota limits. However, it does not cover error behavior, side effects, or authentication requirements. These are not critical for a comparison tool, but more detail would be helpful.

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, no filler. All information is essential and presented upfront. The purpose, parameters, output, performance, and quotas are all included efficiently.

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 complexity (9 parameters, nested objects, no output schema), the description covers the key points: number of strategies, common execution settings, output type (metrics and comparison summary), and performance expectations. It could mention more about return format or error handling, but overall it is sufficient for an agent to understand 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?

Schema description coverage is only 11%, so the description must compensate. It explains that the strategies run on the same pair, interval, and date range, which clarifies the role of those parameters. However, it does not explain the 'capital', 'filters', or 'date_to' parameters beyond what the schema provides. It adds some meaning but not enough to fully cover the gap.

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 defines the tool's action ('Run 2-5 strategies'), the resource ('same pair / interval / date range'), and the output ('per-strategy metrics plus comparison summary'). It distinguishes itself from sibling tools like arena_get_strategy_performance (single strategy) and arena_run_backtest (single backtest).

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: it expects 10-50 seconds, has daily quotas (Pro=20, Power=200), and specifies the API tier. It implies when to use (comparing multiple strategies) but does not explicitly state when not to use or list 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?

With no annotations, the description bears full burden. It explains that returns are scenario numbers and which option wins on expected value, explicitly stating it is not a buy/sell recommendation. It does not disclose any destructive potential, but the tool is purely computational and idempotent, so no contradiction exists.

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 a single, well-structured paragraph that front-loads the purpose. It covers all essential aspects without verbosity, though it could be slightly more concise by omitting the URL and 'free tier' note.

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 absence of an output schema, the description adequately explains return values (scenario numbers and winner on expected value). It covers both modes, input requirements, and the tool's scope, making it complete 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 coverage is 100%, providing per-parameter descriptions. The description adds value by explaining how prices are treated (multiples vs absolute) and the role of each mode, which aids understanding beyond the schema alone.

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 performs decision-math over user assumptions to compare 'buy now' vs 'wait for dip' strategies. It distinguishes between two modes (compare and allocate) and explicitly differentiates from the full interactive version, ensuring the tool's specific purpose is unambiguous.

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 advises to 'Ask the user for the missing inputs, then call,' providing clear usage context. It also mentions the full interactive version for advanced needs, implying limitations. However, it lacks explicit 'when not to use' or direct alternatives among 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?

With no annotations, the description fully carries the burden. It discloses that the tool is descriptive only, never a buy/sell signal, returns structural ladder (not calendar-DCA), cites historical base rate with warnings, and explains the lump-sum-vs-tranche tradeoff. It also mentions the invalidation requirement and API Pro tier.

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 long but well-structured, with the main purpose front-loaded. Every sentence adds value, but it could be slightly more concise. The structure is logical: purpose, what it returns, exclusions, alternatives, and requirements.

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 thoroughly explains the three main returns (ladder, base rate, tradeoff) and mentions that if capital is given, each tranche returns an absolute amount. It also covers the invalidation requirement. This is complete for a complex 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 baseline is 3. The description adds value for several parameters: explains that asset support cluster rungs are BTC-only, invalidation is mandatory, and risk_aversion ladder tilt purpose. This adds meaning beyond the schema for these 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?

The description clearly states the tool frames a dip/accumulation thesis without a recommendation, specifies assets (BTC/ETH/SOL), and details outputs (tranche ladder, base rate, tradeoff). It distinguishes from sibling tools like arena_dip_decision, which uses a different method (EV/Kelly). The verb 'Frame' and resource are specific.

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 when to use (dip/accumulation thesis), what it does not do (no recommendation, not calendar-DCA, not price forecast), and provides alternative (interactive tool at URL). It also mandates an invalidation point and explains the tool composes historical-analog and key-levels 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 exist, so the description alone must convey behavioral traits. It mentions it is a 'daily' snapshot and returns specific data, but lacks disclosure on data freshness, update frequency, rate limits, or authentication requirements. It does not contradict any missing annotations since none are provided.

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, efficiently conveying the tool's purpose, methodology, and outputs without extra words. It is front-loaded with the key metric name and immediately actionable.

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 explains what is returned but omits important context like how often the data refreshes, how to interpret the color scale, and whether the snapshot is real-time. There is no output schema to compensate for these gaps, so the description is only partially complete for an effective tool invocation.

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 only parameter is 'context' with a generic description about explaining the call's purpose. Schema coverage is 100%, so the description adds no additional meaning to the parameter beyond what the schema already states. The parameter itself is meta and not functionally relevant to the tool's operation.

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 provides a daily Altcoin-Season indicator with a specific methodology (v7 Native-Filter) and lists the exact outputs: BTC-Dominance, Alt-Dominance, Layer-1 signals, overall color, and Top-50 snapshot. It distinguishes from the sibling arena_get_altcoin_season_history by indicating this is a current snapshot, not historical.

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 does not provide any guidance on when to use this tool versus alternatives, such as whether it is suitable for real-time analysis or how it complements other market indicators. The only hint is '[Free tier]', which implies accessibility but does not clarify usage 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?

With no annotations, the description carries full burden. It discloses tier-capped clamping of the 'days' parameter (Free 30d/Pro 365d/Power unlimited) and the data fields returned. However, it does not mention rate limits, data staleness, or other behavioral traits.

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?

Single sentence plus parenthetical, no wasted words. Key information is front-loaded (historical snapshots, data fields, tier limits).

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, so description must explain return values. It lists the fields, which is mostly sufficient for a history tool. However, it does not specify the structure (e.g., array of daily objects) or format, leaving minor 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?

Schema description coverage is 100%, baseline 3. The description adds value by explaining the tier-capped clamping behavior for the 'days' parameter, complementing the schema description and providing practical usage context.

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 provides historical daily Altcoin-Season snapshots including overall_color, BTC/Alt/Stable dominance, and BTC price. It differentiates from sibling tool 'arena_get_altcoin_season' by specifying historical data vs. likely current status.

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 explicit guidance on when to use this tool vs. alternatives. The tier-capped info hints at usage limits but does not provide when-to-use or when-not-to-use conditions.

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 carries the full burden. It discloses that the tool is read-only (implied by 'get') and lists the returned data fields. It also mentions the '[API Pro tier]' constraint and 'admin-readable' scope. No mention of rate limits or side effects, but for a get detail endpoint this is adequate.

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 long with no fluff. The first sentence states the scope (YOUR backtest runs) and the second lists what is returned. The tier information is appended concisely. Every word earns its 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 the lack of output schema, the description adequately lists the key return fields (metrics, asset, interval, CAGR, etc.). It does not specify error handling or the exact structure of metrics, but for a detail endpoint this is reasonably complete. Could mention what happens if the ID is not found.

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 both parameters (id, context) have clear descriptions in the schema. The tool description adds minimal additional parameter information beyond what the schema provides, only listing output fields. Baseline of 3 is appropriate as the description does not enhance parameter understanding.

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: retrieving details of a specific backtest run. It explicitly lists the returned metrics (metrics, asset, interval, date range, CAGR/winRate/drawdown, params) and distinguishes itself from siblings like arena_get_backtest_trades and arena_list_backtests.

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 implies the tool is for the user's own backtest runs or admin-readable ones, but does not explicitly state when to use it versus alternatives like arena_list_backtests (for listing) or arena_get_backtest_trades (for trades). No 'when not to use' guidance is provided.

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 full burden. It only adds '[API Pro tier]' as a behavioral constraint. It does not disclose side effects (none expected), error behavior, rate limits, or that it is a read-only operation. The description is insufficiently transparent for a tool with no 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 a single sentence that conveys purpose and tier requirement. It is concise and front-loaded. However, it could be slightly more structured (e.g., separate sentences for purpose and tier) but overall 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?

No output schema exists, so the description should explain the return format. It only mentions 'trades list and per-trade equity progression' without structure, fields, or pagination. Given the tool's complexity (equity curve data), this is incomplete. Also missing error handling 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 description coverage is 100%, so baseline is 3. The description does not enrich parameter meaning beyond the schema. It repeats the field names but adds no additional semantics (e.g., format constraints, common values).

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 'trades list and per-trade equity progression' for a backtest, with a specific verb ('get') and resource ('backtest trades'). It is distinguishable from sibling tools like arena_get_backtest (likely summary stats) by specifying the per-trade and equity curve detail.

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 guidance on when to use this tool vs alternatives. It does not mention prerequisites, exclusions, or compare to siblings like arena_get_backtest or arena_run_backtest. The tier note hints at access requirements but not usage 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?

No annotations are provided, so the description carries the full burden. It discloses the returned data structures (quadrant_performance, component_correlations, asset_correlations, current_quadrant) and mentions the free tier. However, it does not discuss rate limits, authentication, or any side effects, which limits 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 a single paragraph dense with information, effectively listing components and return data. It is concise but could benefit from bullet points or better structure. Every sentence adds value, though the density might reduce 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?

Given no output schema, the description adequately explains the return values (quadrant_performance, component_correlations, asset_correlations, current_quadrant). It covers the key data and purpose but lacks details on pagination, error cases, or performance considerations.

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 description coverage, the single parameter 'context' is fully documented in the schema itself. The tool description adds no additional meaning beyond what the schema provides, so the baseline score 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 clearly states the tool returns 'pre-aggregated weekly correlations between Bitcoin and 13 macro components + 4 asset classes', listing specific components and data fields. The verb 'get' and resource 'BTC macro correlations' are well defined, and it distinguishes from siblings by being specific to BTC macro correlations among many arena 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 notes 'Historical analysis only — not investment advice' but does not provide explicit guidance on when to use this tool versus alternatives. No sibling differentiation or when-not context is given, leaving the agent to infer from the name alone.

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 educational nature, lack of recommendations, and mentions a 'Free tier' hinting at usage constraints. It does not disclose potential limitations like data source or update frequency, but provides reasonable transparency beyond schema.

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, front-loaded with the main purpose and output details. Every sentence adds value with no wasted 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?

Given no output schema, the description adequately lists the return fields (current_trend, last trend change, counts, last-5 fractals). It is sufficient for an educational analysis tool, though it could clarify what 'Phantomflow adaptation' means. Overall complete for its purpose.

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 only parameter is 'context' with a detailed schema description. The tool description does not add new semantics beyond what the schema already provides. With 100% schema coverage, 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 it returns daily Bitcoin market structure including current trend, last trend change timestamp, counts of waves and fractals, and last-5 fractals. The name and title match the purpose, and it distinguishes from siblings by being specific to BTC market structure.

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 notes it is an 'Educational analysis of price action — no signal, no recommendation,' implying its use case is for analysis not trading signals. However, it does not explicitly state when to use this tool versus alternatives like arena_get_volatility_insights or arena_get_key_levels.

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 provided, so description is the sole source. It discloses returns and interpretation (higher count = more signals) and notes 'Free tier', but lacks details on rate limits, authentication, or 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?

Two concise sentences plus '[Free tier]' front-load key details. 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?

For a simple tool with one parameter and no output schema, the description sufficiently explains the return data and interpretation. It is complete enough for the agent to understand what it will receive.

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 description adds no new information about the 'context' parameter beyond what the schema provides. 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 retrieves the current state of the Bitcoin Bullmarket-Ampel, including active count (0-5), stage history, and breakdown. It specifies the resource uniquely among siblings.

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 guidance on when to use this tool versus alternatives like arena_get_btc_market_structure or arena_get_cycle. The description does not explain appropriate context 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, the description must disclose behavior. It details return structure (raw + Z-Score, signal enum, percentiles), states BTC-native indicators are returned as not_applicable for altcoins, and emphasizes the point-in-time nature. It lacks mention of auth or performance limits, but provides significant behavioral context.

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 structured with a clear opening, then details about default and altcoin behavior, and finally return format. It is slightly verbose but each sentence adds value. The '[Free tier]' note is minor extra info.

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 explains the return values comprehensively (raw scores, Z-Score, signal enum, percentiles, and not_applicable fields). It also clarifies the data's nature (point-in-time). However, it could mention the exact indicators for BTC and any size limits.

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 value by explaining the asset parameter options and the resulting behavior (e.g., BTC-native indicators not applicable for altcoins). This goes beyond the schema's enum descriptions. The context parameter is well-described in the schema, so the description doesn't detract.

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: 'Crypto cycle position — where are we in the cycle?' It specifies it's a point-in-time 10-indicator aggregation for BTC and a price-derived read for ETH/SOL, distinguishing it from sibling tools that focus on individual indicators.

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 explains default BTC usage and how to pass asset=ETH or asset=SOL for altcoin cycle reads. It also notes that BTC-native indicators are returned as not_applicable for non-BTC assets, providing clear guidance on usage. However, it does not explicitly state when to avoid this tool in favor of 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 burden. It discloses the tier-capped range behavior but does not mention data freshness, update frequency, authentication requirements, or any other behavioral traits. It is adequate but minimal.

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 a single sentence with a parenthetical, front-loading the key information. Every part earns its place with no wasted 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?

Given no output schema, the description explains what the tool returns (historical series) and the tier limit, but does not explain the meaning of 'adj_score' and 'z_adj_score' or how the data is structured. For a simple tool, it is adequate but could be more 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?

Schema coverage is 100% and the parameter descriptions already include auto-clamping by tier. The description adds the specific tier limits, but this is marginal value 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 returns 'Historical daily BTC-Cycle adj_score + z_adj_score series', specifying the exact data and time granularity. This distinguishes it from sibling tools that return other metrics.

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 mentions tier-capped ranges (Free 30d, Pro 365d, Power unlimited), giving some context on when to use based on subscription. However, it does not explicitly say when not to use this tool or suggest alternatives among the many 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?

With no annotations, the description carries the full burden. It discloses the tool is read-only ('returns mean/max/outlier counts'), the data source (bgeometrics vs BRK), and a usage note ('[API Pro tier]'). This adequately informs the agent about the tool's behavior and constraints, though it could mention whether historical data is persisted.

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 a usage note) and front-loaded with the essential purpose. Every sentence adds value: the first defines the tool, the second details output, and the third provides context. There is 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?

Given the tool has only two parameters and no output schema, the description adequately covers what the tool returns (mean, max, outlier counts) and its intended use case (BRK-migration review). It does not describe edge cases or pagination, but for a simple data retrieval tool, this is sufficient.

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% (both parameters have descriptions). The tool description adds the phrase 'for the requested window,' which implicitly references the 'days' parameter, but does not elaborate beyond what the schema already provides. Thus, it meets the baseline expectation without adding significant new 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 starts with 'Daily drift log comparing bgeometrics (legacy) vs BRK (canonical-soon) pilot metric pairs,' providing a specific verb (comparing), resource (metrics), and scope (daily drift). It clearly distinguishes from siblings like arena_get_gem_score or arena_get_sentiment by naming the exact comparison, making the tool's unique purpose immediately clear.

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 states 'Used by BRK-migration review (every 4 weeks),' offering a clear context for use. However, it does not mention when not to use this tool or suggest alternatives (e.g., for ad-hoc queries), leaving the agent without explicit exclusion criteria.

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 full burden. It discloses key behaviors: returns verdicts (with thresholds for helps/neutral/hurts/insufficient_data), aggregates across backtest runs, evaluates filters in isolation, and provides median CAGR values after trading costs. It mentions the 'Free tier' context, adding value beyond the schema.

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) and front-loaded with the main purpose. It uses efficient punctuation and includes all essential information without verbosity. Every sentence adds value.

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 (2 required) and no output schema, the description covers the return values (verdict, baseline/filtered CAGR), the aggregation method, and the filter isolation. It could clarify whether the tool returns data for all filters at once, but overall it is sufficiently complete for selection and invocation.

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 global context (explaining the verdict logic and output format) but does not enhance per-parameter semantics beyond what the schema already provides. Baseline score is 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 clearly states the tool's purpose: it provides an aggregated analysis of how Pro+ entry filters affect strategy CAGR across all backtest runs for a given market. It specifies the output (verdict, baseline/filtered CAGR) and distinguishes itself from siblings like arena_get_strategy_filter_effect by focusing on an aggregated, platform-wide analysis with verdicts and median values.

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 implies the tool is used to get filter effect insights, but it does not explicitly state when to use this tool versus alternatives like arena_get_strategy_filter_effect. No guidance on prerequisites (e.g., need a Pro+ subscription) or context where this tool is preferable.

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 discloses key behavioral traits: returns current value, classification, recent history, and a cache for change-detection. However, it omits details like whether the tool is read-only, any rate limits, or the lifespan of the cache. Adequate but not comprehensive.

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 packed with useful information. 'Free tier' is somewhat ambiguous but not detrimental. Efficiently front-loads the core functionality.

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 adequately lists what the tool returns (value, classification, recent history, cache). This compensates for the lack of formal output schema, making it complete enough for agent use.

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 description adds no new meaning to the sole parameter 'context'. The parameter's description in the schema already covers its purpose (analytics). Baseline 3 applies as the description does not compensate further.

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 retrieves the Crypto Fear & Greed Index from alternative.me with historical context, and lists specific return elements (value, classification, recent history, cache). This distinguishes it from sibling tools like arena_get_sentiment or arena_get_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?

No explicit guidance on when to use this tool over alternatives like arena_get_sentiment or arena_get_pulse. The mention of 'Free tier' is vague and does not help an agent decide.

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 '[API Pro tier]' restriction and indicates the analysis performed (baseline vs filtered comparison), but lacks details on rate limits, required data, or 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?

The description is a single efficient sentence that packs information about the action, filters, metrics, and a usage tier note without 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?

Given no output schema, the description mentions the key metrics (CAGR, win-rate, drawdown) but does not describe the response structure. The essential purpose and inputs are clear, making it mostly 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?

Schema coverage is 100% and the schema description for the 'context' parameter is detailed. The tool description does not add additional meaning beyond what the schema provides, so baseline score 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 'Lift analysis of entry filters' and lists specific filters and metrics (CAGR, win-rate, drawdown), distinguishing it from sibling tools like arena_get_strategy_insights and arena_get_strategy_performance.

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 implies usage for filter analysis but does not explicitly state when to use this tool vs alternatives, nor does it mention exclusions 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?

No annotations provided; description bears full burden. It explains output and sign meaning, and mentions free tier, but lacks detail on authentication, rate limits, error handling, or data freshness. Adequate but not comprehensive.

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, no fluff. Front-loaded with purpose, then details. Every sentence adds value.

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 read tool with good schema coverage, the description covers what it returns, sign meaning, and free tier. Lacks mention that history is available via sibling, and could explain the context parameter's use, but overall sufficient.

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% (1 parameter fully described in schema). The tool description adds no additional context beyond the schema's own description for the 'context' parameter, so 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?

The description specifies the exact resource ('Binance Perpetual Funding Rate') with cadence ('8h'), clearly states it returns value, 30d MA, and Z-Score, and distinguishes from sibling 'arena_get_funding_rate_history' which would provide historical 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 implies usage for the latest snapshot, but does not explicitly state when to use or when to prefer the history sibling or other tools. No exclusion criteria or alternative guidance is provided.

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, and the description discloses minimal behavioral traits beyond the data source and tier limits. It does not mention safety (e.g., read-only), rate limits, or idempotency, which are important for an agent to assess risk.

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 extremely concise with two sentences that front-load the most critical information: source, cadence, and tier limits. Every word earns its place, making it efficient for an agent to parse.

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 is somewhat incomplete as it does not hint at the return format (e.g., array of objects). However, it adequately covers the essential aspects for a simple data retrieval tool with tier constraints.

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 both parameters are described in the schema. The description adds marginal value by explaining the tier clamping in context, but does not provide additional semantic meaning beyond what the schema already offers.

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 specifies 'Historical Binance Perpetual aggregated funding rates (8h cadence)', which identifies the exact data source, product, aggregation, and cadence. This distinguishes it from sibling tools like 'arena_get_funding_rate' for current rates and other historical 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?

The description does not provide explicit guidance on when to use this tool versus alternatives. While 'Historical' implies it's for historical data, it fails to mention the sibling 'arena_get_funding_rate' for current rates or any conditions for use.

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 full burden. It mentions Pro+ gets raw factor values but doesn't clarify what free tier returns (e.g., a summary? limited data?). No disclosure of rate limits, authentication needs, or whether this is read-only. The behavioral impact of tier differences is vague.

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 with no filler. Front-loaded with the core action and resource. Every word earns its 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 is too sparse. It does not explain what the score represents, how to interpret the return value, or what the factors are. For a complex tool in the altcoin domain, more context is needed for an agent to use it effectively.

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 no new meaning beyond what the schema already provides. It repeats the coingecko_id format example and does not elaborate on the 'context' parameter's purpose beyond the schema's detailed description. The description adds minimal value to parameter understanding.

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 retrieves an Altcoin Screener score for a specific coin using its CoinGecko ID. It distinguishes from siblings like arena_get_gem_scores by specifying 'for one coin', and mentions tier differences (Pro+/Free). The verb 'get' and resource 'gem_score' are explicit.

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 explicit guidance on when to use this tool versus alternatives. While it mentions tier differences, it doesn't direct the agent to use this for single-coin queries versus other tools for multiple coins or different analyses. Sibling tools include many similar arena_get_* functions, but no selection criteria are provided.

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 fully bears the burden. It reveals tier-based access limitations, refresh frequency, and the composite factor methodology. Lacks details on potential rate limiting or authentication requirements, but provides substantial behavioral context.

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 two sentences, front-loaded with purpose and key detail about composite factors and tier limits. Every sentence adds value without 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?

Given the lack of output schema, the description hints at return size (top-N per tier) but does not describe the output structure (e.g., rank, score components). Still, it provides enough context for a ranking tool, though could be more 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?

Schema description coverage is 100%, so baseline is 3. The description adds context about the scoring model and tier gating but does not add meaning beyond the schema for parameters like 'limit' and 'from_rank', which are already well-described in 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?

Title 'Get Altcoin Screener Rankings' and description clearly state it provides altcoin rankings based on a composite score of three factor groups (Mean-Reversion, Tokenomics, Market-Structure). It distinguishes itself from numerous sibling tools by specifying the data source (CoinGecko Top-200) and the backtest-validated nature, not a hype list.

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?

Description explicitly mentions tier limits (Free top-10, Pro top-50, Power top-200) and daily refresh, helping agents decide when to use. However, it does not explicitly exclude alternatives or compare to similar tools like arena_get_gem_score.

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 carries full burden. It discloses the frequency ('Bi-weekly'), weighting ('equal-weight'), and metrics shown (CAGR, max drawdown, win-rate). It also mentions tier-based limitations. However, it does not indicate whether the tool is read-only, authentication requirements, rate limits, or data freshness.

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 long, with the first sentence stating the core functionality and the second providing tier information. It is front-loaded and every word adds value, making it highly concise and well-structured.

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 parameters, no output schema), the description covers the essential aspects: what it does, its frequency, output metrics, and tier limitations. It could be more complete by mentioning the return format or how the screener picks are defined, but it is sufficient for an agent to understand its use.

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 parameter details are already present. The description adds value by explaining the default behavior for top_n ('Free: top-10 default. Pro+: custom N.') and the output metrics (CAGR, max drawdown, win-rate), which go 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: 'Bi-weekly equal-weight basket backtest for Top-N screener picks vs BTC and market average.' It specifies the action (get validation) and resource (altcoin screener picks), and the title further clarifies. This distinguishes it from siblings like arena_get_backtest, which is a different type of backtest.

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 usage context by noting tier limitations: 'Free: top-10 default. Pro+: custom N.' This implies when to use the default vs custom N. However, it does not explicitly state when to use this tool over alternatives like arena_get_backtest or arena_get_backtest_trades, nor does it include when-not-to-use conditions.

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 full burden. It discloses that the tool returns moving averages and interprets them, and mentions it is from Charles Edwards and free tier. However, it does not mention rate limits, authentication requirements, or what happens if data is unavailable. The description is adequate but not rich in behavioral detail.

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, concise and front-loaded with the key information: what the tool returns and its interpretation. Every sentence adds value with no extraneous 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?

Given the tool has one parameter, no output schema, and no annotations, the description provides enough context: it returns the moving averages and explains the signal. It could be more complete with details on return format or additional data fields, but it is sufficient for understanding the tool's purpose.

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 schema description coverage is 100% with a detailed description of the 'context' parameter. The tool description adds no additional meaning to the parameter beyond what is already in the schema. Baseline 3 is appropriate since schema already covers parameter semantics.

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 returns the latest Hash Ribbons indicator, specifically the 30d and 60d hashrate moving averages, and explains what the signal means. It uses specific verbs ('Returns') and resource ('Hash Ribbons indicator'), and distinguishes itself from siblings like arena_get_cycle or arena_get_fear_greed by focusing on hashrate moving averages.

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 implies usage for detecting miner recovery (bullish signal) when 30d > 60d after a capitulation, but it does not explicitly state when to use this tool versus siblings. No direct guidance on when not to use or mention of alternatives. The '[Free tier]' tag hints at accessibility but is insufficient as usage 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 provided, the description carries the full burden. It discloses that the output is a distribution (not a recommendation), requires point-in-time indicator history, includes effective-n and small-n warnings, and mentions the API Pro tier. It does not cover error cases or rate limits, but the behavioral traits are adequately described for a read-only analytical 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?

The description is moderately long but every sentence adds value: the opening question engages, followed by output details, data source, preset definitions, asset constraints, and pricing. It is well-structured and front-loaded with the core purpose, though slightly verbose.

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 output schema, the description adequately explains the return structure (median/IQR/positive-share, horizons, effective-n). It also covers use cases, presets, and asset limitations. Missing details on error behavior or empty results, but overall 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?

All parameters have schema descriptions (100% coverage), and the tool description adds significant context: it explains the meaning of each preset, the asset restrictions for ETH/SOL, detailed instructions for the 'context' parameter, and default forward horizons. This goes beyond the schema to clarify usage.

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 returns a conditional forward-return distribution for a named preset cycle state, detailing the metrics (median/IQR/positive-share) and horizons. It distinguishes itself from sibling tools by noting it is not obtainable from web search or public APIs, and specifies unique presets like cycle_bottom_cluster.

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 explains when to use the tool (to see historical analog forward returns based on cycle state) and provides guidance on asset and preset compatibility (e.g., fear-greed presets are BTC-only). It does not explicitly state when not to use it, but the context is clear enough for the given sibling toolset.

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 provided, so description must disclose behavioral traits. It mentions backfill dates and free tier, but does not describe destructive potential, auth needs, rate limits, or response format. Adequate for a read-only tool but lacks some detail.

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?

Concise two-sentence description plus backfill/free tier note. Front-loaded with core purpose. Every sentence adds value without 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?

No output schema, but the description lists all returned metrics (DVOL, ATM vols, realized vol, vol risk premium) which provides sufficient context. Includes backfill dates and free tier. Does not detail return format or interpret numbers, but adequate 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 description coverage is 100%, so baseline is 3. The description does not add significant meaning beyond the schema's parameter descriptions (currency enum and context). Merely restates what's in 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?

Clearly states it provides the latest Deribit volatility snapshot for BTC/ETH, listing specific metrics (DVOL, ATM implied vols, realized vol, vol risk premium). Distinct from sibling tools like arena_get_volatility_insights.

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 mentions usefulness for position sizing, options strategies, and market regime assessment, giving clear context for when to use. Does not specify exclusions or 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?

No annotations are provided, so the description carries the burden. It discloses that the tool returns status and eventually the full result, which is sufficient for a polling tool. However, it does not explicitly state that it is safe to poll repeatedly or mention any rate limits, which could be improved.

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, highly concise, and front-loaded with the primary action ('Polls an async job'). Every word serves a purpose, with 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?

The description covers purpose, usage source, return values, and even a free-tier note. Without an output schema, it explains the return structure well. It does not detail polling frequency or error handling, but for a simple status check tool, it is fairly 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?

Schema coverage is 100% (2 parameters fully described). The description adds value by explaining that job_id is a UUID from arena_run_universe_backtest, but the schema already covers both parameters adequately. The context parameter's description in the schema is already very detailed.

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 polls an async job by job_id, specifies the source (arena_run_universe_backtest), and lists return fields. It distinguishes itself from sibling tools that fetch static data or not directly related to async jobs.

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 implies usage after creating an async job via arena_run_universe_backtest, providing clear context. It lacks explicit when-not-to-use or alternatives, but the sibling list contains many other get_ tools making this purpose distinctive.

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 provided, so the description carries full burden. It discloses the tool is descriptive only, aggregates swing fractals, and returns zones with specific attributes (touch count, band, distance, etc.). It clarifies it is not predictive, which is key. However, it does not mention rate limits, data freshness, or any potential side effects, though none are expected.

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 concise sentences plus a list of output attributes. It is front-loaded with the core purpose, includes a clear disclaimer, and avoids unnecessary detail. Every sentence adds value.

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 thoroughly explains the return structure: zones with touch count, band, last-touch date, signed distance, and ordering. It covers the tool's scope and limitations, making it complete for a single-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?

Schema coverage is 100% with one parameter 'context' fully described in the schema. The description does not add meaning beyond what the schema provides; it focuses on the output. 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 tool's purpose: 'Reproducible Bitcoin support/resistance zones' by aggregating swing pivots into price zones with touch counts and distance. It distinguishes itself from many sibling tools by being a mechanical clustering alternative to eyeballing fractal charts, and explicitly states it is not a prediction or buy/sell 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 explains when to use (for mechanical S/R zones) and when not (not for predictions/signals). It also notes it's from the free tier, implying no cost barrier. However, it does not explicitly name alternative tools for prediction use cases or provide context on when to prefer this over other 'get_' tools like arena_get_btc_market_structure.

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 full burden. It discloses that the operation is a fetch (read-only), mentions access tier gating ('Free tier; per-object access additionally gated by min_tier'), and describes the response structure including optional graph traversal 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 front-loaded with the core purpose, followed by return details and optional behavior. It is appropriately sized for the tool's complexity, though slightly verbose with the include_graph explanation.

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 thoroughly explains the return envelope (payload, explanation, provenance, ontology binding, compute version) and the graph traversal option. All 5 parameters are covered in context, and the free tier constraint is noted, making it complete 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 coverage is 100%, baseline 3. The description adds value beyond schema by explaining include_graph in detail (resolved edges, api_path, seo_slug), clarifying as_of ('Omit for latest'), and providing examples for type and subject (e.g., 'market_regime', 'GLOBAL').

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 fetches a Knowledge Object by type+subject, lists what is returned (payload, explanation, provenance, ontology binding, compute version), and distinguishes itself as the single tool covering all knowledge types, differentiating from list and other getter siblings.

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 context for using the include_graph parameter and implies use for retrieving specific knowledge objects. However, it does not explicitly compare with siblings like arena_list_knowledge or arena_get_ontology_term, nor provide when-not-to-use 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?

Details all return fields including composite_score, regime_label, cycle_phase_label, matrix_quadrant, tier_scores, components, and stale_components_detail with freshness quantification. No annotations provided, description carries full burden and does so thoroughly.

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?

Single sentence captures core purpose and all return details efficiently, though slightly long.

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 but description exhaustively lists all return fields and explains the stale_components_detail feature, making it complete for a complex 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?

Only one parameter (context) with schema coverage 100%; description does not add additional meaning beyond the schema's detailed instructions.

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?

Clearly states it provides a 'Daily Macro Regime snapshot' from 18 components in 6 tiers with specific weights, distinguishing it from other arena_get_* tools that focus on individual indicators.

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?

Description implies use for macro regime assessment but lacks explicit guidance on when to use vs alternatives 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?

No annotations provided, so description carries full burden. It discloses data source (Deribit Public API), collection frequency (daily 02:00 UTC), and mentions free tier. Clearly indicates read-only behavior with no destructive actions. Lacks details on response format but covers key behavioral aspects.

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 with key information front-loaded. No extra words. Efficiently communicates purpose and data returned.

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, description fully details what is returned (fields for last expiry and upcoming expiries with counts). Input parameters are adequately covered. Complete for a simple data retrieval 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?

Input schema has 2 parameters (market, context) with full descriptions in schema (100% coverage). Description adds no significant meaning beyond schema; 'market' enum is already clear. Baseline 3 is appropriate as 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?

Clearly states it returns max pain data for Deribit BTC options, including last finalized expiry with specific fields (max_pain_strike, spot_at_expiry, etc.) and up to 10 upcoming expiries. Distinguishes from sibling 'arena_get_max_pain_history' by focusing on latest and upcoming 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?

Implies usage for obtaining latest and upcoming max pain data, but does not explicitly state when to use this tool versus alternatives like 'arena_get_max_pain_history' for historical data. Mentions data freshness (daily UTC) but no clear when-not-to-use or 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?

With no annotations provided, the description carries full burden. It discloses that data is historical and finalized, and that days are auto-capped by tier ('Pro 365d, Power 3650d'). It also mentions the API tier requirement. This is adequate for a read-only historical data 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?

The description is concise at two sentences plus a note, with the core purpose front-loaded. Every sentence adds value: it states the resource, columns, use case, and behavioral constraints.

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, but the description lists all output columns, mitigating the gap. It explains tier capping and the use case. For a history tool returning a table, this is sufficient, though pagination or ordering details 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 has 100% coverage, so baseline is 3. The description adds specific tier cap values ('Pro 365d, Power 3650d') which enhances the parameter documentation beyond the schema's generic 'capped by tier'.

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 provides historical finalized Deribit BTC options expiries, with specific columns listed. The name and title align, and it distinguishes itself from sibling tools like 'arena_get_max_pain' by emphasizing 'history' and 'finalized'.

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 'Useful for backtesting Max Pain theory', providing a clear use case. It does not explicitly state when not to use or mention alternatives, but the purpose is well-defined.

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. It mentions '[Free tier]' indicating availability but lacks details on authentication, rate limits, data freshness, or side effects. Some behavioral context is provided but minimal.

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 very concise with two sentences plus a short note. It is front-loaded with the definition and provides thresholds efficiently. No extraneous content.

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 defines the metric and thresholds but does not specify the output format (e.g., numeric value, object). Given no output schema, this is a gap. It also lacks information on data source or update frequency. Adequate but incomplete.

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% as the only parameter 'context' has a description in the schema. The tool description adds no additional meaning beyond the schema, so 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 gets the 'Latest Mayer Multiple,' defines it as BTC-Price ÷ 200-day SMA, and provides threshold values. It is a specific verb+resource and distinguishes from the sibling `arena_get_mayer_multiple_history` by implying current value.

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 context about the metric and thresholds but does not explicitly state when to use this tool versus alternatives like the history tool. Usage is implied but not detailed.

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 full burden. It mentions tier-capping and limits, which is partially helpful. However, it does not disclose rate limits, authorization needs, or the fact that days are auto-clamped (already in schema). The behavioral disclosure is adequate but not thorough.

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?

Exceptionally concise: one sentence conveys core function and tier constraints. Every word adds value, no fluff. 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?

Given low complexity and no output schema, the description covers the essential aspects: what the series represents and tier limits. It does not describe return format or pagination, but for this tool, it is largely sufficient.

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 description does not need to add parameter meaning. It adds no extra context beyond the schema descriptions (e.g., days auto-clamped, context usage). 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?

Description explicitly defines the tool as retrieving historical Mayer-Multiple values (BTC-Price / 200d SMA). It provides the formula and tier limits, making the purpose clear. However, it does not differentiate from sibling tools like arena_get_mayer_multiple (current value) or other historical series 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?

No guidance on when to use this tool versus alternatives (e.g., arena_get_mayer_multiple for current value). No preconditions, exclusions, or context for selection are provided.

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 bears full burden for behavioral disclosure. It mentions auto-capped date ranges by tier but omits key traits like auth requirements, return format, error handling for invalid series_id, or rate limits.

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 very concise with two sentences and a bracketed note, front-loading the main purpose. No extraneous information, though it could be slightly more informative.

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 three parameters, no output schema, and no annotations, the description is insufficient. It lacks explanation of what 'BRK' means, how to find valid series_ids, what the output format is, and how the 'context' parameter should be used effectively.

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 baseline is 3. The description adds value by explaining the 'days' parameter's capping behavior and tier-dependent limits (Free 30d / Pro 365d / Power unlimited), which is not in 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 states it returns a historical time series for a BRK on-chain metric, which is clear in verb and resource. However, it does not differentiate itself from sibling tools that also return historical data for specific metrics (e.g., arena_get_mayer_multiple_history), reducing clarity.

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 guidance is provided on when to use this generic tool versus the many specific history tools in the sibling list. The only contextual hint is the date range cap by tier, which is implicit.

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 provided, so description carries full burden. It states the tool is on the free tier and returns specific fields, implying non-destructive read behavior. However, it does not disclose rate limits, error handling, or authentication 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 two sentences, both front-loaded with key information. The first sentence states the core action, and the second sentence clarifies the input source and output format. No 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?

Given the simple nature of the tool and full schema parameter coverage, the description adequately covers what the tool does and how to use it. The return structure is explicitly stated, compensating for the lack of an output schema.

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 examples for series_id (e.g., 'mvrv', 'sopr', 'realized_price'). This provides marginal additional context beyond the schema, which already describes the 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 retrieves the latest value of a BRK on-chain series, specifies that series_id comes from arena_list_onchain_series, and lists the return fields. This distinguishes it from sibling tools that provide historical 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 implies usage by referencing the series_id source, but lacks explicit when-to-use vs. alternatives or exclusions. For a single-value retrieval tool among many historical tools, this is minimally adequate.

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 bears full burden. It discloses what the tool returns (label, definition in EN/DE, calculation, unit, source, source_ref, version, related terms). It also mentions '[Free tier]', hinting at usage limits, though not fully detailed. 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 four sentences and front-loads the core action and return value. It is efficient but could be more structured. Still, every sentence adds value.

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 lookup tool with no output schema, the description fully covers purpose, input semantics, return fields, and usage context. It is complete and leaves no major gaps.

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%, but the description adds value by giving an example for 'term' and explaining the 'context' parameter's purpose and formatting requirements (15-25 words, third-person). This goes beyond the schema's basic description.

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 resolves a knowledge-platform term to its canonical definition, with an example (term='regime') and lists return fields. It is distinct from sibling tools, which focus on other data like strategies, backtests, or market metrics.

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 use this tool to resolve onto:<term>@<version> references inside Knowledge Objects, providing clear context. No explicit when-not-to-use is given, but the intended use case is well-defined.

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 full burden. It discloses the return values (score, band, label, color, deltas, verdict, components, score_percentile) and notes '[Free tier]' indicating pricing. It does not disclose rate limits or auth needs, but for a read-only tool, this is sufficient.

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, packing key information into a few sentences with no wasted words. It front-loads the purpose and lists components efficiently.

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 no output schema, the description adequately explains the return structure including components and percentile. It lacks data type details or example values but is sufficient for an AI agent to understand the output.

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 description does not add meaning beyond the input schema, which already covers the only parameter ('context') with full schema coverage (100%). 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 tool returns a daily 0-100 heat score for the Bitcoin market, aggregated from 8 components, and lists the components. This distinguishes it from sibling tools like arena_get_cycle or arena_get_fear_greed, which return individual components.

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 implies usage for obtaining a composite Bitcoin market heat score but does not provide explicit when-to-use or when-not-to-use guidance, nor does it compare with alternatives like individual component tools or other composite 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 full burden. It discloses ascending order and tier-based range caps. It does not mention destructiveness or side effects, but the tool is clearly read-only.

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, no extra words. Front-loaded with purpose, each sentence adds value: output content, ordering, and tier limits.

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 historical data retrieval tool with no output schema, the description sufficiently hints at output structure (date, score, band) and ordering. It does not cover pagination or limits beyond tiers, but those are reasonable omissions.

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 baseline is 3. The description does not add additional meaning beyond the schema; the schema already explains the 'days' parameter and its auto-clamping.

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 returns historical daily Arena-Pulse scores with date, score, and band. It is distinct from siblings like arena_get_pulse (current) and other historical tools by name and content.

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 mentions the historical nature and tier-based range, but does not explicitly state when to use this tool versus alternatives. The context of 'historical' is implied, but not contrasted with other 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 full burden. It discloses the polling nature, lifecycle, and return fields, but does not mention idempotency, rate limits, or error handling. It adequately describes core 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 very concise: two sentences, front-loaded with the action, and no unnecessary words. Every sentence adds value.

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 explains key return fields (progress_pct, counts, pdf_url/xlsx_url). It could mention response format or error cases but is largely complete for a simple polling 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 baseline is 3. The description adds no extra meaning beyond the schema; both parameters are described in the schema clearly (job_id as UUID from checkout, context with formatting instructions).

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 'Poll' and identifies the resource as 'Custom-Report job'. It clearly states the lifecycle stages and return fields, distinguishing it from siblings like arena_get_job_status which may be more generic.

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 implies usage for tracking job progress after checkout, but does not explicitly state when to use this tool versus alternatives or provide exclusion conditions.

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 mentions '[Free tier]' for cost but lacks behavioral details such as authentication needs, rate limits, data freshness, or what exactly the response contains beyond 'one multi-source view'.

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 one sentence with a dash-separated list, efficiently conveying the core components. It is front-loaded and concise, though could be slightly more structured.

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 should clarify the return structure. It mentions 'one multi-source view' but does not specify fields or how to request ticker-level sentiment. This leaves significant gaps 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 baseline is 3. The description adds 'Configurable period' but does not add meaning beyond the schema's enum for period. The 'context' parameter has detailed schema documentation; the description doesn't add extra semantics.

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: aggregates multiple sentiment indicators (Fear & Greed, funding-rate, Altcoin-Season, Arena-Pulse) into one multi-source view, with optional ticker-level sentiment. This distinguishes it from sibling tools that provide individual indicators.

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 implies usage for a composite sentiment view but does not explicitly state when to use this versus alternatives like individual indicator tools. No when-not or exclusion criteria are mentioned.

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 provided, so description carries full burden. Mentions 'read-only' and '[Free tier]' but lacks details on rate limits, return format, or any restrictions beyond being public.

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 with front-loaded purpose. No unnecessary words. Every sentence earns its 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?

No output schema, so description should explain return values; it does not. Otherwise, for a simple read tool with 2 params, it covers the basics but lacks return info.

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. Description does not add extra meaning beyond what schema already provides for the two 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?

Clearly states read-only access to a publicly shared backtest by share-id. Distinguishes from sibling 'arena_get_backtest' by specifying 'shared' and 'public' access.

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 anyone can fetch and that it's used for sharing with non-users, providing clear context for when to use. Does not list alternatives or when not to use, but context is 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?

With no annotations provided, the description carries full burden. It discloses the prerequisite (active Ampel) and notes the 'Free tier' cost implication. However, it does not mention potential side effects, rate limits, or the nature of the data source beyond the cron. More behavioral detail would be beneficial.

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, front-loaded with the primary purpose, and includes essential context. Every word adds value 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?

Given no output schema, the description could explain the return format (e.g., what green/yellow/red means) or provide more details on data freshness. It covers prerequisites and tier but leaves some aspects incomplete for a tool with moderate 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 four parameters. The description adds minimal meaning beyond the schema; it mentions 'e.g. 'rsi_sma'' for strategy, which is already in the schema. Baseline 3 applies as 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?

The description clearly states the tool returns current signal-status (green/yellow/red) for a specific strategy, pair, and interval. It uses specific verbs and resources, distinguishing it from other status tools in the sibling list, e.g., arena_get_bullmarket_ampel or arena_get_sentiment.

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 some usage context by mentioning it requires at least one user with an active Ampel and is backed by a daily cron. However, it does not explicitly state when to use this tool versus alternatives, nor does it provide when-not or exclusion criteria.

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 provided, so description carries full burden. It discloses the data source (Binance) and includes a disclaimer about context only, but lacks details on rate limits, caching, or whether the data is live vs. delayed. Adequate but could be more 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?

The description is extremely concise: three sentences front-load the purpose, usage guidance, and disclaimers without any redundant or extraneous information. Every sentence adds value.

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 effectively explains what the tool returns (last price, 24h change, high, low) and its context of use. Could briefly mention output format, but for a simple data tool, it's sufficiently 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?

Schema coverage is 100%, and the 'context' parameter is well-documented in the schema. The description adds no additional parameter meaning, so a baseline score of 3 is appropriate given 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?

The description clearly states the tool fetches current spot prices for BTC, ETH, and SOL, specifying it provides USDT-quoted last price, 24h change, high, and low from Binance. This distinguishes it from sibling tools that focus on other analytics or different assets.

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 advises using the tool to anchor analytics with current market price instead of switching to web search, providing a clear use case. Lacks explicit when-not-to-use or alternatives among siblings, but the guidance is strong for its 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?

No annotations are provided, so the description carries the full burden. It mentions the data source (DefiLlama peggedUSD) and that it's free tier, but does not describe read-only nature, data freshness, or return format. This is adequate but leaves gaps.

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 a single, dense paragraph that wastes no words. Every sentence adds value: purpose, differentiation, specific outputs, source, and pricing tier. Front-loaded with main 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?

The description covers purpose, outputs, source, and cost. It lacks details on update frequency, pagination, or any limitations. For a simple data-fetching tool with no output schema, this is nearly 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 only parameter (context) has a detailed description in the schema, covering its purpose and usage rules. The tool description adds no additional semantic information beyond what the schema provides. 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 aggregates stablecoin supply as a liquidity proxy and lists specific outputs (current supply, 30d/90d change, acceleration, time series). It distinguishes itself from arena_get_macro_regime, which only provides a 30d delta.

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 tells when to use this tool (to see trend beyond a single delta) and explicitly says it is 'Descriptive only, not a signal.' However, it does not explicitly state when not to use it or list alternative tools beyond macro_regime.

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 details the returned data: baseline-stats, each filter variant's stats with CAGR/drawdown/win rate deltas, best_by_cagr pick, and not_applicable_filters. It notes the analysis is based on real backtest aggregations and mentions [Free tier], hinting at cost implications. It provides sufficient behavioral context.

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 [Free tier] tag. The purpose and usage are front-loaded. Minor verbosity in the second sentence could be trimmed, but overall it is well-structured and concise.

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 thoroughly covers what the tool returns (baseline-stats, deltas, best pick, excluded filters) and its basis (real aggregations). Given no output schema, it provides enough context for an agent to understand the tool's output and invocation purpose.

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 description does not need to add parameter details. It mentions interval default '1w' and strategy/asset roles 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?

Description clearly states it provides per-(strategy, asset, interval) filter-effect analysis, with specific output fields (baseline-stats, filter variants with deltas, best_by_cagr, not_applicable_filters). The verb 'get' and resource 'strategy filter effect' are explicit, and it distinguishes from siblings by focusing on filter effect comparison rather than general strategy performance.

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?

Description directly answers the use case: 'Which filters would improve my backtest for X on Y?'. It also clarifies it uses real backtest aggregations not theoretical permutations. However, it does not explicitly state when not to use or mention alternatives, leaving slight room for improvement.

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 carries the full burden. It discloses the tier limitation (Free Top-10 vs Pro+ full) and the difference in detail between modes. However, it does not mention auth requirements, rate limits, data freshness, or potential side effects. This is adequate but not comprehensive.

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 extremely concise at two sentences, front-loading the core purpose and then efficiently explaining modes and tier limits. Every sentence adds essential information with no wasted 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?

Given the tool has 7 parameters (1 required), no output schema, and no annotations, the description explains modes, tier limits, and parameter relationships well. It lacks details about return structure (e.g., matrix format), but the functional behavior is sufficiently clear for an AI 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 coverage is 100%, so baseline is 3. The description adds value by explaining the relational logic between strategy and interval parameters (together trigger detail mode) that goes beyond individual parameter descriptions. This semantic addition justifies a 4.

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 'aggregated backtest performance per (strategy × interval) cell.' It distinguishes between two modes (matrix vs detail) and specifies tier limitations. This is a specific verb+resource combination that differentiates it from sibling tools like get_strategy_performance.

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 explains when to use each mode: if both strategy and interval are provided, detail mode; otherwise matrix mode. It provides clear context for usage but does not explicitly mention when not to use or suggest alternatives, which would earn 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?

No annotations provided, so description carries full burden. It describes return fields and mentions 'Free tier' implying limitations, but doesn't specify read-only nature, authentication needs, rate limits, or side effects. Adequate but not exhaustive.

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?

Three sentences, front-loaded with core purpose. Every sentence adds value: purpose, return fields, sibling differentiation, example question, free tier note. No 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?

Given 6 parameters, no output schema, the description lists return fields comprehensively and specifies scope (single combination). Lacks details on error handling or pagination, but sufficient for typical usage.

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% (baseline 3). Description adds value beyond schema: case-insensitivity for asset, detailed context parameter guidance with example, defaults for interval and ref_strategy. Enhances usability.

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 states it returns aggregated backtest performance for one specific (strategy, asset, interval) combination and lists return fields. Distinguishes from sibling arena_get_strategy_insights for multi-strategy overview.

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 (single combination) and when not to (use arena_get_strategy_insights for multi-strategy). Provides example user question 'How does strategy X perform on asset Y?'.

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 carries full burden. It discloses the response structure (regime buckets with trades, win_rate, avg_pnl_pct, reward_risk_ratio, share_of_time_pct, rating, and live recommendation). It also notes the reward_risk_ratio is per-trade mean/stddev, not annualized Sharpe. No mention of destructive behavior or authentication needs, but the tool appears read-only and safe.

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, front-loaded with purpose. It efficiently packs essential details: regime categories, output fields, and live recommendation. Every element earns its place without verbosity.

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 complexity (regime splitting, live recommendation, multiple metrics), the description covers key aspects. It lists output fields, explains metrics, and notes the scope. However, it lacks information about data range, historical depth, or limitations (e.g., number of trades required for reliability). Still, it is mostly 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?

Schema coverage is 100% with detailed parameter descriptions. The description adds value by explaining the regime classification logic, the derived metrics, and the requirement for the 'context' parameter (15-25 words, third person). This goes beyond the schema alone.

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 title and description clearly identify the tool as retrieving historical backtest performance split by macro market regime, plus a current live regime recommendation. It specifies the scope: ONE (strategy, asset, interval) combination. This distinguishes it from similar tools like arena_get_strategy_performance (general) and arena_compare_strategies.

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 tool answers 'Should I trade this strategy NOW?' and focuses on a single combination. It provides context for when to use: when regime-aware performance and live recommendation are needed. However, it does not include explicit when-not-to-use statements or suggest alternative 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 provided, so description carries full burden. Does not disclose read-only nature, rate limits, or authorization needs. Only mentions 'Free tier' which vaguely implies no cost but insufficient.

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?

Single sentence, no fluff. Could benefit from slightly more detail without becoming verbose.

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?

Tool has two required params and no output schema. Description mentions 'pair list' but omits other return fields, format, or example. Incomplete for effective agent use.

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 schema already explains parameters. Description adds no extra meaning beyond schema, meeting baseline but not exceeding.

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 states 'Detail view of one universe, including pair list' and title 'Get Universe Detail' clearly indicates purpose. Slightly vague without explicit verb like 'retrieves' but sufficient and distinct from listing sibling.

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 guidance on when to use this tool versus alternatives like arena_list_universes. The '[Free tier]' hint is minimal and does not differentiate from other get 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 burden. It mentions the API tier restriction and the output (CAGR breakdown), but does not disclose authentication needs, rate limits, or other behavioral traits beyond what is stated.

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 front-load the key output and use case, with a tier note. Every sentence adds value with no wasted 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?

Given no output schema, the description explains the output nature and purpose. It lacks details on return format or asset scope, but is sufficient for an agent to understand the tool's role among many siblings.

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 67%, with context and min_trades described. The description does not add meaning beyond the schema; asset_type is only defined by its enum. 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 it provides CAGR breakdown by volatility phase per asset and timeframe, and it identifies the use case (finding regime-fit for strategies). This distinguishes it from siblings like arena_get_volatility_phases and arena_get_volatility_recommendations.

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 implies usage for regime-fit analysis but does not explicitly state when to use this tool versus alternatives or provide exclusions. Siblings exist but no guidance 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?

With no annotations, the description adds update frequency ('updated daily at 08:00 UTC') and pricing tier ('Free tier'), but lacks disclosure of authorization needs, rate limits, or whether the operation is read-only.

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 with four sentences: output definition, update time, use case, and tier. No wasted words, and key 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?

The description adequately covers the tool's purpose, scope, and update schedule. Although no output schema exists, the expected return values (phase strings) are simple enough that the description suffices.

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 does not add meaning beyond the schema for the two parameters; the asset_type enum description and context parameter are already documented in the input 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 verb 'returns', the resource 'volatility phase', and specifies the scope (Top-10 Crypto, Stocks, ETFs) and update frequency, distinguishing it from sibling volatility 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 provides clear context by stating 'useful for regime-aware strategy selection', but does not explicitly exclude when not to use it or name alternatives among the many 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?

With no annotations provided, the description carries full burden. It discloses key behaviors: ranking by historical win-rate, phase detection from latest snapshot, minimum trade threshold, and the API tier requirement. It does not cover edge cases like insufficient data or phase detection failure, but the transparency is adequate.

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 brief usage note and tier indicator. Every sentence is essential, no redundancy, and the main purpose 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?

Although there is no output schema, the description explains the output (top-3 strategies with win-rate). The tool has 3 parameters (2 required), and the description covers input and behavior adequately. It could mention error handling or result format in more detail, but it is sufficient for an agent to use 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%, but the description adds significant value: it clarifies the 'pair' parameter with examples, provides detailed usage instructions for 'context' (length, perspective, sensitivity), and 'asset_type' has an enum and default. This guidance goes beyond the schema descriptions.

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 action: 'Returns top-3 strategies ranked by historical win-rate for the current volatility phase of a given asset pair.' It specifies the resource (top-3 strategies), condition (current volatility phase), and asset pair, distinguishing it from siblings like arena_get_strategy_performance or arena_get_volatility_phases.

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 an explicit use case: 'Use this to answer "which strategies work best right now for BTC?"' and mentions a constraint: 'Minimum 20 trades per phase required for inclusion.' While it does not explicitly state when not to use, the context is clear enough for appropriate selection.

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 the tool is public and free tier, but does not disclose potential rate limits, authentication requirements, caching behavior, or error handling. The description is adequate but not comprehensive.

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, front-loading the core purpose and filtering capabilities. Every sentence adds value without redundancy. It is concise and well-structured.

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 simplicity of the tool (retrieving a list) and no output schema, the description covers the return type (top-100 CAGR winners), origin (across all users, anonymized), filters, and pricing tier (free). It could optionally mention that the limit parameter controls the number of results, but overall it is quite complete for effective use.

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 description adds meaning beyond the schema by stating the tool is filterable by asset_class and strategy, which corresponds to the asset_type and strategy parameters. The context parameter has a detailed description in the schema itself, so repetition is unnecessary. However, the limit parameter is not explained in the description, though its schema provides constraints.

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 explicitly states it returns a public top-100 list of highest-CAGR backtest results across all users with anonymized usernames, filterable by asset_class and strategy. This clearly defines the tool's function and distinguishes it from sibling tools like arena_get_backtest which return individual results.

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 does not provide explicit guidance on when to use this tool versus alternatives among the many sibling tools. It implies usage for obtaining aggregated top winners (public, free tier), but lacks direct exclusions or alternative recommendations.

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 description carries full burden. Mentions pagination, filters, and tier, but does not state read-only nature, error behavior, or rate limits.

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, front-loaded with main purpose, 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?

Adequate for a listing tool with no output schema, but could mention return format or ordering. Missing details are minor given sibling tool commonalities.

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?

Description lists filterable and pagination parameters, but adds little beyond schema names. Schema coverage is low (29%), so description should compensate more.

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?

Clearly states verb 'lists' and resource 'your own backtest runs', and distinguishes from siblings by specifying filterable fields and pagination.

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?

Implies usage for listing user's backtests with filters, but no explicit when-not-to-use or alternatives among 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?

No annotations are provided, so the description must carry the full burden. It discloses that new types appear automatically and mentions the 'Free tier', but does not cover idempotency, error scenarios, or permission requirements. It is adequate but not rich.

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 tag, with no wasted words. It front-loads the core purpose and each sentence adds value. The structure 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's simplicity (one parameter, no output schema), the description provides enough context: return fields, relationship to sibling, and automatic updates. It lacks details on possible empty results or errors, but it is largely complete for a list 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 schema already fully describes the single 'context' parameter with detailed instructions. The description adds no further meaning to the parameter, so 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 tool lists all published knowledge types and subjects with specific fields. It explicitly differentiates from the sibling 'arena_get_knowledge' by instructing to use this tool first to learn valid pairs.

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 when-to-use guidance: 'Use this BEFORE arena_get_knowledge to learn valid type/subject pairs instead of guessing.' It implies usage context but does not explicitly list when not to use it or mention alternatives beyond the one sibling.

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 provided, but description clearly states it returns id + label + group and is a read-only list operation. Could mention any limits or pagination, but not necessary for a fixed set of 21 metrics.

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, no filler, front-loaded with purpose. Every word earns its 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?

Tool is simple list operation; description covers return values (id, label, group), usage guidance, and access tier. No output schema needed.

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 parameter is 'context' with full schema coverage. Description adds no extra semantics; baseline 3 is appropriate as schema already documents it.

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 it lists all available BRK on-chain series, specifies 21 metrics (MVRV, NUPL, etc.), and distinguishes from siblings by noting the id is used with other 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?

Explicitly tells to use the id with arena_get_onchain_latest/_history, providing clear guidance on when to use this tool and what to do with output. Also indicates free tier access.

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 fully convey behavioral traits. It describes the tool as listing strategies and being filterable, but does not explicitly state it is read-only or mention any rate limits, data freshness, or other constraints. The [Free tier] note is somewhat ambiguous.

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 extremely concise: three sentences covering what the tool does, filtering options, usage context, and a pricing note. Every sentence is essential with no wasted words, and the most important 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 listing tool with no output schema, the description adequately explains the return content (key, label, plan, etc.) and its role in the workflow. It lacks details on pagination or result limits, and the [Free tier] note could be clearer, but overall it provides sufficient context for effective use.

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 schema already documents parameters. The description adds context by stating filterability by asset class and plan (matching schema), but does not elaborate on 'lang' or 'context' beyond schema descriptions. It does add value by listing return fields, which aids parameter understanding indirectly.

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 lists backtest strategies with specific details (key, label, plan, asset classes, indicators) and explicitly distinguishes its role as a precursor to arena_run_backtest, differentiating it from sibling tools like arena_get_strategy_performance or arena_compare_strategies.

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 guidance: 'Use this before calling arena_run_backtest to discover valid strategy names.' This clearly indicates when to use the tool, though it does not explicitly mention when not to use it or alternatives, which would strengthen the score further.

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 full burden but only mentions 'returns all active subscriptions for the current API key' and '[API Pro tier]'—the latter is useful but the description does not disclose any other behavioral traits like rate limits, data freshness, or mutation 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?

The description is extremely concise—one sentence plus a tier note—with no redundant information. It front-loads 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?

Despite the tool's simplicity, the description does not explain what 'subscriptions' are (e.g., live signals, alerts), nor does it mention return format or any required setup. Given no output schema, more context is needed for 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?

The single parameter 'context' has 100% schema description coverage, so the description adds no new meaning. Baseline 3 is appropriate as the schema already fully documents the 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 'Returns all active subscriptions for the current API key,' using a specific verb and resource. It is distinct from sibling tools like arena_cancel_subscription or arena_subscribe_cycle_changes, though it does not explicitly differentiate from those.

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 guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, when-not-to-use, or comparisons to other list/subscription 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 correctly identifies the operation as listing (read-only) and notes a free tier, but it fails to disclose any rate limits, data freshness, pagination behavior, or the fact that no side effects occur. The description is too minimal to fully inform an agent about behavioral traits.

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 a single, well-structured sentence that immediately conveys the tool's action and purpose. It includes examples and a context note about the free tier, making it efficient with no wasted 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?

For a simple listing tool with one parameter and no output schema, the description adequately explains what the tool does and how the output is used. It could briefly mention that the operation is read-only or indicate whether the list is exhaustive, but overall it is reasonably complete given the low 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% because the only parameter 'context' is fully described in the schema. The tool description adds no additional semantics for the parameter beyond what the schema already provides, such as the required length and third-person perspective. 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 uses a clear verb ('lists') and specific resource ('asset universes') with concrete examples (BTC, top-10 crypto). It distinguishes the tool's purpose by linking to custom-report and universe-backtest endpoints, making it evident what value it provides and differentiating it from sibling 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 implies usage by stating it lists universes and includes a '[Free tier]' hint, but it offers no explicit guidance on when to use this tool vs alternatives like arena_get_universe, nor does it mention any prerequisites or exclusions. The context is clear but lacks depth for decision-making.

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 bears full responsibility. It discloses that the tool returns a quote without committing to a purchase, and explains behavioral differences for crypto vs. stocks/etf. However, it does not discuss side effects, error scenarios, or authentication requirements, leaving some gaps.

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 extremely concise: two sentences with no wasted words. The first sentence front-loads the core purpose and outputs, and the second provides asset type differentiation. Every sentence earns its 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 the tool's complexity (9 parameters, nested objects, no output schema), the description covers the main purpose and asset type distinctions. However, it lacks details on output format, error handling, and state effects (though it implies no mutation). Combined with no annotations, it could be more comprehensive for safe invocation.

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 56%, meaning some parameters already have descriptions. The description adds context by summarizing that universe_tier='custom' requires custom_pairs and that crypto uses top-N tiers. However, it does not explain other parameters like interval, period_label, or strategy_params in detail, adding marginal 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: getting a pricing quote for a custom report without committing to a purchase. It specifies the resource (custom report), verb (get quote), and what is returned (price, universe size, preview, etc.). It also distinguishes between crypto and stocks/etf usage, differentiating it from sibling tools like arena_run_universe_backtest.

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