mcp-server

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

With no annotations, the description bears full responsibility for behavioral disclosure. It reveals what the tool checks and returns (risk scores, flags, verdict), implying a read-only analysis. It does not mention permissions, rate limits, or data sources, but the core behavior is well communicated.

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 with zero waste: first sentence defines purpose and scope, second lists checks, third describes output and usage. Each sentence adds distinct value, making it highly 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 presence of an output schema (documenting return structure), the description covers the tool's operation and output adequately. Minor gaps include parameter format details, but overall it provides sufficient context for an AI agent to decide when and how to use the tool.

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

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

Schema coverage is 0%, so the description must compensate. It mentions 'pool_address' only implicitly through the tool's purpose, without specifying format (e.g., hex prefix, length) or constraints. For a single parameter, more explicit guidance is needed to ensure correct invocation.

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

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

The description clearly identifies the tool as an Aerodrome DEX pool risk assessment on Base, specifying the exact checks (honeypots, rug pulls, hidden ownership, tax manipulation) and the output (per-token risk scores, flags, AI verdict). This differentiates it from sibling tools like contract_check or token_due_diligence.

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 'Use before providing liquidity,' giving a clear use case. It doesn't mention when not to use or compare with alternatives, but the context is sufficient for an AI agent to understand the intended application.

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 must cover behavioral traits. It only states the data scope but does not disclose update frequency, data source, or whether it's read-only. This is insufficient for an agent to understand operational details.

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 a single, clear sentence with no extraneous information. It lists commodities concisely and mentions the trend period.

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

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

For a simple no-parameter tool with an output schema, the description is adequate but minimal. It could benefit from adding data frequency or source to help the agent understand freshness and reliability.

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 zero parameters, so baseline is 4. The description correctly adds no parameter information since none exist.

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 global agricultural commodity prices for a specific list of commodities including a 6-month trend. It implicitly distinguishes from siblings like energy_markets or industrial_metals by focusing on agricultural items.

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. With many sibling tools covering commodities, explicit when-to-use or when-not-to-use information is missing.

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 that the tool returns aggregate and individual ratings, price target with metrics, a signal, and recent upgrades/downgrades. It also mentions cost ($0.05) and data source (Financial Modeling Prep), which aids transparency, though it does not cover rate limits or error 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 in the first sentence, then succinctly details return fields, usage, and context. Every sentence adds value, and 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 an output schema exists, the description still provides complementary details about return values (consensus, price target, signal, upgrades/downgrades). It also explains how the tool fits into a broader analysis with sibling tools and notes cost and source, leaving no obvious gaps 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 description coverage is 0%, but the description fully compensates by explaining the parameter: 'Pass symbol=<ticker> (default AAPL).' This tells the agent the parameter name, type, and default value, completely covering what the schema lacks.

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 'Wall Street analyst consensus for a stock' and enumerates the returned data (rating breakdown, price target, signal, upgrades/downgrades). It distinguishes from sibling tools insider_trading and congress_trades by positioning them as companions covering different groups (corporate insiders, Congress).

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 instructs 'Pass symbol=<ticker> (default AAPL)' and frames usage in the context of building a 'smart-money picture' alongside sibling tools. It implies when to use this tool (for analyst sentiment) vs. alternatives (insider trades, Congress trades), though does not formally list 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 and discloses key behaviors: scans the first 3 blocks, returns risk score, bundle wallets, and dump status. It implies a read-only analysis without stating authorization needs, but is generally 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 concise with two sentences that front-load the core action and outcome. Every sentence adds value, and there is no redundant or extraneous 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?

Given a single required parameter and an output schema (presumably defining the return values), the description covers the essential inputs and outputs. Minor gaps exist in parameter details, but overall it is sufficiently complete for a focused detection 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 has 0% coverage and the only parameter 'address' is not described in the description beyond its type string. It does not clarify the address format (e.g., token contract address) or provide examples, requiring the agent to infer from 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 the tool's purpose: 'Token launch bundle and sniper detection on Base' with a specific verb 'scans' and scope 'first 3 blocks after launch'. It distinguishes from siblings like 'token_launches' by focusing on coordinated buys and risk assessment.

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 advises 'Use before buying any new token to check if the launch was bundled', providing clear when-to-use guidance. However, it does not mention 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 carries the full burden. It describes the tool as a risk monitor that returns scores and narratives, but does not disclose any behavioral traits such as authentication needs, rate limits, or side effects. Since it is a read-only monitoring tool, the lack of such detail is somewhat mitigated, but transparency could still 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, front-loaded with the purpose, and contains no extraneous information. Every sentence 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 has zero parameters and an output schema exists (as indicated by context signals), the description covers the essential information: output metrics (risk score, USD exposure, risk narrative) and context (Morpho Blue markets). It is sufficient for an agent to understand what the tool provides, though it could mention that the output schema details the return format.

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

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

The tool has zero parameters, and the schema coverage is 100%. The description adds no parameter information because none exist. According to the guidelines, a baseline of 4 is appropriate when there are no 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 it is a 'DeFi liquidation cascade risk monitor' and specifies it tracks collateral-at-risk curves across Morpho Blue markets. It lists outputs (risk score, USD exposure, AI risk narrative), making the purpose specific. However, it does not explicitly differentiate from sibling tools like defi_risk or liquidations, though the Morpho Blue focus provides some distinction.

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 the tool is 'critical for assessing systemic DeFi risk,' implying when to use it. However, it does not provide explicit guidance on when not to use it or mention alternatives. Usage context is implied but not fully elaborated.

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?

Describes refresh interval (15 minutes) and additional endpoints. No annotations are provided, so the description carries the full burden. It lacks details on authentication or error behavior, but for a read-only tool, 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 concise with no redundancy. It front-loads purpose, lists outputs, provides usage guidance, and states refresh interval in a clear, well-organized manner.

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

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

With no parameters and an output schema present, the description covers all needed context: what it does, what it returns, when to use it, and behavioral traits. Nothing essential is 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?

There are no parameters, making schema coverage 100% trivially. The description adds value by listing the output data fields, which compensates for the absence of 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 it provides on-chain intelligence for Base and Ethereum, listing specific data points (whale_alerts, dex_volume_24h, gas_price_gwei, TVL rankings). This distinguishes it from siblings like 'whale_alert' due to its broader scope.

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

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

Explicit use cases are given: monitoring whale movements, spotting DEX volume spikes, tracking DeFi health. It does not explicitly mention when not to use or direct to alternatives, but the 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 for behavioral transparency. It discloses the tool returns aggregated data (most-bought/most-sold tickers with counts), is based on lagged STOCK Act disclosures, and costs $0.05. It also mentions the 30-day window and the underlying data being behind ETFs like NANC and KRUZ. While it does not detail update frequency or latency, for a simple read-only tool with no parameters, the transparency is good and no contradictions exist.

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

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

The description is three sentences: first states the main function, second provides output details and context, third gives data source and companion tools. Every sentence adds value, no redundancy. It is appropriately sized for a tool with no parameters.

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 parameters and an existing output schema (though not shown), the description explains the type of output (tickers, counts), data source (STOCK Act), timeframe (30 days), and related tools. It is complete for a signal aggregation tool, providing enough information for an agent to invoke it correctly.

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

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

The tool has zero parameters, and schema coverage is trivially 100%. The description adds no parameter semantics because there are none. Per guidelines, baseline for 0 parameters is 4, and the description provides context about what the tool returns without needing to explain 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 aggregates congressional buy/sell signals over the last 30 days, returns most-bought and most-sold tickers with trade counts. It distinguishes itself from sibling tools like 'congress_trades' and 'InsiderFlow' by noting it provides an aggregate signal rather than per-ticker detail. The verb 'aggregate' and resource 'US congressional buy/sell signal' are 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?

The description implies usage as a 'quick read on where congressional money is flowing' and notes it is a companion to 'congress_trades' and 'InsiderFlow', suggesting when to use this tool (overview) vs alternatives (detail). However, it does not explicitly state when not to use it or list exclusions, such as requiring recent data or handling specific timeframes beyond 30 days. The context is clear but lacks explicit prohibitions.

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

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

Description discloses key behavioral traits not in annotations (none provided): data is lagged, disclosure-based, not real-time; sourced from STOCK Act filings; returns recent transactions with transaction and disclosure dates. No annotations to contradict, so full credit.

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 concise with no wasted words. It front-loads the purpose, then methodically covers what it returns, how to use the symbol parameter, a key limitation (lag), companion tool, and cost. Every sentence adds essential 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?

Given the simple input schema (1 optional parameter) and presence of output schema, the description is complete. It covers data source, fields returned, filtering, latency characteristics, companion tool, and cost. An agent has enough to decide when and how to use it 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?

With 0% schema description coverage, the description fully compensates by explaining the symbol parameter: 'Pass symbol=<ticker> to filter to trades in one stock (e.g. NVDA); omit for the most recent trades across all members.' This adds complete meaning beyond the schema's sparse definition.

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 returns US congressional stock trades with specific fields (ticker, direction, amount range, dates) from STOCK Act filings. It distinguishes itself from sibling tools like insider_trading (corporate insiders) by specifying 'trade like Congress' signal and mentioning 'Companion to InsiderFlow.'

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 explains when to use (for congressional stock trade signal), how to filter with symbol parameter (explicitly shows example NVDA), and notes the disclosure lag (median ~25 days, up to 45+), implying not for real-time. It also mentions a companion tool (InsiderFlow) and cost ($0.05 via x402), providing full 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 the full burden. It discloses that values are nominal, the source (US Census), frequency (monthly), and cost ($0.05). It does not mention any destructive behavior, aligning with its read-only nature.

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 efficiently conveys purpose, return data, source, frequency, cost, and usage context. Every sentence adds value, and the structure is well-organized.

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 0 parameters and an output schema (mentioned in context), the description provides a thorough overview of the return values and their interpretation. It is fully complete 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?

The tool has 0 parameters, so the schema coverage is 100% by default. The description adds value by explaining what the tool returns, which is sufficient for a parameterless tool.

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

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

The description clearly states it's a 'US consumer-demand signal' and lists specific return data (retail sales, core measure, sector breakdown, consumer phase). It distinguishes itself from the sibling tool 'cycle_pulse' by describing itself as the demand-side mirror.

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 'Use it to read whether the US consumer is accelerating or cooling and gauge discretionary demand.' It also notes its companion tools, providing context for when to use it. While it doesn't list exclusions, the single-purpose nature makes this sufficient.

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

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

No annotations are provided, so the description must disclose behavioral traits. It mentions the cost ($0.15 via x402) and that it produces four outputs in one call, which is helpful. However, it does not disclose rate limits, idempotency, or failure modes, 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 two sentences, front-loading the action and listing the outputs, followed by usage guidance and cost. Every sentence contributes 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 tool's simplicity (one parameter, clear output schema exists), the description covers the input type, output formats, best use cases, and cost. It is complete enough for an agent to select and 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?

The input schema has one parameter (url) with 0% description coverage. The description adds meaning by explaining the URL is for research reports, blog posts, or news articles, and that it will be repurposed into content. This compensates for the schema's lack of 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 repurposes any URL into four specific content formats (LinkedIn post, tweet thread, newsletter section, SEO meta summary), which is a specific verb+resource+outputs. No sibling tool has similar purpose, so it is well-distinguished.

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?

It says 'Best for turning research reports, blog posts, or news articles into ready-to-publish social content,' providing context for when to use. While it doesn't state when not to use or alternatives, the sibling tools are all unrelated, so no exclusion is necessary.

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 description carries full burden. It discloses returned fields and detection capabilities (hidden admin keys, proxies), but omits potential side effects, rate limits, or authentication needs. Behavior is mostly read-only, but limitations are unstated.

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: first defines purpose and output, second provides use-case guidance. No redundant information, perfectly 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 an output schema exists (not shown but inferred), the description sufficiently covers return values and use case. However, it omits error handling, chain parameter details, and any limitations, leaving minor gaps for a complete context.

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

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

Schema coverage is 0% and description fails to explain the 'chain' parameter or its default value 'eth'. While 'address' is intuitively covered, the lack of chain guidance forces reliance on schema defaults. Description should enumerate possible chains or note cross-chain support.

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 does 'smart contract verification for any EVM address' and lists specific returned fields (verified, is_proxy, etc.), distinguishing it from sibling tools like 'smart_contract_audit' by focusing on pre-interaction checks for hidden admin keys and proxies.

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 says 'Use before interacting with an unknown contract', providing clear context for when to apply the tool, but does not name alternative sibling tools for deeper audits.

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 returns specific data, sources (US Census, public domain), and cost ($0.05 via x402). As a zero-parameter read-only tool, it implicitly signals non-destructive behavior. It does not mention auth or rate limits, but the information is sufficient for a low-risk data retrieval 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 front-loaded with a clear tagline, followed by a structured list of returned data, usage guidance, source, and cost. Every sentence serves a purpose with no redundancy. It is appropriately sized for the tool's complexity.

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

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

Given the tool has no parameters and an existing output schema, the description thoroughly explains the return values, use cases, and provenance. It is complete for an agent to understand when and why to invoke this tool 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?

The input schema has zero parameters, and schema coverage is 100%. According to the rubric, baseline is 3 with no param info. The description does not add parameter information because there are none, but it compensates by detailing the rich output. This meets the baseline expectation.

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 US inventory and production cycle signals including inventory-to-sales ratio, new orders, backlog, and cycle phase. It distinguishes itself from sibling tools by branding as 'the bullwhip gauge for the real economy' and positioning as a companion to supply-chain and macro data.

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

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

The description provides explicit use cases: 'time the manufacturing cycle, anticipate industrial demand and commodity pull-through, and read restocking vs destocking.' It does not mention when not to use or explicitly name alternatives, but the context is clear and actionable.

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

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

No annotations are provided, so the description carries full burden. It discloses what the tool returns (TVL, audit status, exploit history, etc.) and explains the two modes (specific protocol or overview). It does not mention side effects or authentication, but the read-only nature is implied by the context and contents. Additional detail about output schema or behavior would push it to 5.

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 the tool's purpose and contents, followed by usage instructions. No unnecessary words, perfectly 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?

Given the tool's complexity and the presence of an output schema, the description covers all essential aspects: risk metrics, yield data, and input parameter options. It provides enough information for an agent to decide when and how to use it.

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

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

The schema has zero description coverage for the one parameter. The description explicitly explains the parameter's semantics: 'Pass protocol name or leave empty for top protocols overview,' which adds significant meaning beyond the schema itself.

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 performs DeFi protocol risk assessment covering TVL, audit status, exploit history, smart contract risk, and yields. It distinguishes from related sibling tools like 'smart_contract_audit' and 'rwa_risk' by focusing on DeFi protocols and including yield 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?

Description provides implicit usage guidance: 'pass protocol name or leave empty for top protocols overview.' It does not explicitly state when to use this tool versus alternatives or when not to use it, but the context implies it's for DeFi-specific risk queries.

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 returned data (last 4 quarters metrics) and parameter constraints (days_soon default 7, max 90). However, it omits details on rate limits, authentication needs, or data freshness (real-time vs delayed), which are common for financial tools.

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 short sentences each carrying useful information. It front-loads the purpose and data details, then covers parameter usage 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 tool's moderate complexity (two optional parameters, output schema provided), the description covers the returned data and parameter semantics. A minor gap is the ambiguity of empty tickers (whether it returns all or nothing), but overall the description is sufficient for an agent to effectively invoke the tool.

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

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

Schema description coverage is 0%, so the description compensates by explaining tickers as a comma-separated string and days_soon as a near-term window with default and max. It also describes the output data, adding value beyond the schema's parameter names and default 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 the tool provides earnings dates, estimates, and beat/miss history for the last 4 quarters, including EPS actual/estimate, surprise percentage, day-after price reaction, and consecutive beats. This differentiates it from sibling tools which focus on other financial data like analyst ratings or insider trading.

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 how to use parameters (comma-separated tickers, days_soon window) but does not explicitly state when to use this tool versus alternatives like analyst_ratings or insider_trading. The context is clear enough for an agent to infer usage for earnings-specific queries.

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 lists the data content but does not disclose behavioral traits such as read-only nature, rate limits, or authorization requirements.

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 concise sentence that front-loads the purpose and lists key data items without unnecessary words. It could be slightly more structured but 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 no parameters and the existence of an output schema, the description adequately covers what the tool returns. It does not mention update frequency or data source, but is sufficient for a simple 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?

The tool has zero parameters, and the input schema covers 100% of them. According to the rubric, 0 params yields a baseline of 4; no additional parameter information is needed.

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

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

Description uses specific verb 'intelligence' and clearly identifies the resource as US energy markets, listing specific data types (WTI, Brent, Henry Hub, etc.) which distinguishes it from sibling tools like agricultural_commodities or industrial_metals.

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 US energy data via the geographic scope, but does not provide explicit guidance on when to use this vs. alternatives, nor any exclusions or 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 mentions 'cached 30 min', which is useful behavioral context. However, it does not disclose authentication requirements, rate limits, or whether the tool is read-only or mutating.

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, using a single sentence to convey the tool's purpose, outputs, and scope. It is front-loaded with the main function ('Equity intelligence'), but lacks structural elements like bullet points.

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 one parameter and no annotations, the description adequately covers what the tool returns and caching behavior. However, it omits input format details and usage context, making it minimally sufficient but not thorough.

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 0% for the only parameter 'ticker', and the description does not explicitly define what the parameter expects (e.g., ticker symbol format). It implies US stocks and ETFs but lacks precision.

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 equity intelligence including buy/hold/sell signals, fundamental ratios, and AI analysis for US stocks and ETFs. The verb is implied (analyze) and resource is specified, but it does not explicitly differentiate from sibling tools like 'tech_analysis' or 'analyst_ratings'.

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 siblings. The description does not mention alternatives or exclusions, leaving the agent to infer context from the tool 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 exist; the description carries full burden. It lists return components (annualized rates, breakdowns, alerts, bias) but does not disclose data freshness, latency, access requirements, or whether it is read-only. Partial 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?

Four concise sentences with clear structure: what it provides, signals, breakdown, and param usage. 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?

Given one optional parameter and existence of an output schema (not provided), the description covers the main return fields. Missing details like data timeframe or real-time vs historical, but sufficient for a funding rates 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 has one parameter with 0% coverage; the description adds 'filters to a single coin', explaining the effect. However, it does not enumerate the exact allowed values (though assets are listed in the context). Good additional value.

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

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

The description clearly states it provides perpetual futures funding rates across major exchanges and specific assets, with signals and breakdowns. It distinguishes well from sibling tools which cover unrelated domains like pools, commodities, etc.

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 funding rate data but lacks explicit guidance on when to use versus alternatives. No when-not-to-use or context comparison is provided, though sibling tools are dissimilar.

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 that the tool returns risk_score, conflict signals, commodity impact, and that leaving region empty gives global overview. However, it does not state idempotency, authorization needs, or whether it is read-only. 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?

Three sentences: first details outputs, second explains parameter usage, third gives usage advice. No wasted words, well-structured, and front-loaded with key information.

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

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

For a simple tool with one optional parameter and an output schema, the description covers inputs, outputs, and usage context comprehensively. 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?

Description adds meaning to the single parameter 'region' by stating 'Pass a region name or leave empty for global overview.' This is beyond the schema, which only provides type and default. Fully compensates for low schema coverage.

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 performs geopolitical risk assessment by region, with specific outputs (risk_score, conflict signals, commodity impact). It distinguishes from siblings like 'supply_chain_intelligence' or 'macro_indicators' by its explicit focus on geopolitics and commodity effects.

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 says 'Use when geopolitical events may affect a trade, supply chain, or commodity position.' This provides clear context for when to invoke, though it does not mention when not to use or suggest alternative tools.

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

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

No annotations provided; description only mentions return types (agency breakdown, amounts, narrative) but no behavioral traits like read-only, 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 sentences, front-loaded with key actions and outputs, 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?

Output schema exists, so return explanation is adequate, but missing usage guidelines and parameter semantics for a moderate-complexity 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 description coverage is 0%; only 'min_amount' is implied by '$10M+' in description. No explanation of 'agency' or 'days_back' parameters beyond schema.

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

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

The description clearly states it retrieves federal contract awards $10M+ and cross-references with stock tickers, but does not explicitly differentiate from sibling tool 'gov_edge_opportunities'.

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?

Implied usage for market-moving contracts, but no explicit when-not or alternatives mentioned. Siblings like 'contract_check' or 'gov_edge_opportunities' exist without differentiation.

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 returning solicitations with urgency flags and AI BD briefing, but does not disclose rate limits, authentication needs, behavior when queries return zero results, or any side effects. The description is 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?

Two sentences, front-loaded with purpose and key features. No wasted words. Could list parameters more systematically, but still efficient.

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

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

Given the tool has an output schema (not shown), the description appropriately omits return value details. However, with 0% schema coverage and many siblings, it should provide more context about each parameter and usage scenarios. Missing 'days_back' explanation is a shortfall.

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 0%, so description must explain parameters. It mentions three filters (keyword, naics, set_aside) with examples for set_aside (SBA/8A/WOSB/HUBZone/VOSB/SDVOSB), but does not mention the 'days_back' parameter at all. This leaves a 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 states the tool searches active federal contract opportunities from SAM.gov, listing specific output fields (deadlines, urgency flags, agency, NAICS code, etc.) that distinguish it from siblings like 'gov_edge' or 'lease_edge'. The verb 'Search' and resource 'federal contract opportunities' 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?

No guidance on when to use this tool versus its many siblings (e.g., 'gov_edge', 'contract_check'). There is no mention of prerequisites, limitations, or scenarios where another tool would be better.

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 provides key behavioral info: real-time data, spot prices, and cost ($0.05 via x402). It is a read operation with no side effects. While some details like authentication or rate limits are missing, the description adds sufficient transparency for a simple query 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 a single sentence, well-structured, and front-loaded with the main action. It avoids redundancy and includes only essential information. 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?

For a tool with no parameters and an output schema, the description fully covers what the tool does and what it returns. It lists the output fields and the cost, making it complete for an agent to understand without additional context.

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

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

The tool has zero parameters, so schema coverage is 100%. The description does not need to add parameter information. Baseline of 4 is appropriate as there are no parameter gaps to fill.

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: returning real-time GPU compute spot prices. It specifies the GPU models (H100, H200, etc.), providers (Vast.ai, RunPod, etc.), and output fields (best_deals, market_signal, infrastructure brief). This is a specific verb-resource combination with high 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?

The description does not explicitly state when or when not to use this tool. However, given the sibling tools are all in different domains (e.g., agriculture, politics, weather), the context implies it's for GPU pricing. More explicit guidance would improve this.

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 for behavioral disclosure. The description does not mention whether the tool is read-only, any rate limits, authentication requirements, or potential side effects. The context implies it is a data retrieval tool, but explicit disclosure is missing.

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 four sentences, front-loading the core purpose and use cases. The region codes are listed compactly. A minor improvement could be removing the trailing period after region codes for consistency, but overall 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?

The tool has an output schema, so return values are documented elsewhere. The description covers purpose, usage guidance, and parameter semantics. However, it does not mention data freshness, update frequency, or any prerequisites, which would be helpful for a real-time intelligence 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 single parameter 'region' has a default empty string in the schema. The description adds significant value by explaining the valid region codes (CISO, ERCO, etc.) and clarifying that leaving it empty returns data for all regions. This fully compensates for the 0% schema description coverage.

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 provides US electricity grid intelligence including real-time demand, generation mix, and grid stress signals. It distinguishes itself from sibling tools by focusing on grid data, while siblings cover other domains (e.g., agricultural commodities, analyst ratings, weather forecast).

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 gives use cases: 'optimize when to run industrial operations, charge EV fleets, or shift compute workloads to low-cost/clean energy periods.' It also lists valid region codes. However, it does not mention when not to use this tool or provide alternatives, though siblings are listed separately.

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: analyzes repo, writes code, runs tests, opens PR, returns pr_url, and costs $0.50. However, it omits potential side effects (e.g., does it modify the repo directly?) and authorization requirements (e.g., GitHub token).

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

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

The description is concise, front-loaded with purpose, and logically structured: identity, actions, usage, best cases, extras, cost. 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 3 parameters (1 required), no annotations, and an output schema (though not detailed in description), the description adequately covers input requirements and return value (pr_url). It could mention expected output structure or prerequisites (e.g., GitHub access), but overall complete for a coding agent 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 0%, so description must compensate. It explains 'task' as a task description and 'repo' as optional URL, adding meaning beyond schema. 'Context' is implied via 'complex multi-step tasks with context' but not explicitly mapped. Two of three parameters are clarified.

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 hires an autonomous coding agent that analyzes a GitHub repo, writes code, runs tests, and opens a pull request. This specific verb-resource combination distinguishes it from siblings like 'contract_check' or 'wallet_risk' which are unrelated.

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 passing a task description and optional repo URL, and recommends use for 'well-scoped coding tasks: bug fixes, feature additions, test coverage, refactors.' It also mentions additional capabilities like hunting bounties and web research, providing clear context despite lacking explicit exclusions or sibling comparisons.

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 discloses real-time nature, momentum signals, category analysis, and cost. However, it does not mention data update frequency, authentication needs, or rate limits, leaving some behavioral 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?

Three concise sentences with no waste. Each sentence adds critical information: purpose, specific coverage, and cost/endpoint. Well-structured and front-loaded.

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

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

Given zero parameters and a rich output schema, the description is fairly complete for a data listing tool. It covers what, which metals, and cost. Could mention data frequency, but overall adequate.

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

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

The tool has no parameters, so schema coverage is 100%. The description adds value by detailing the content (specific metals, momentum, category analysis) beyond an empty schema, earning a baseline of 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 provides real-time prices for 13 specific industrial metals with momentum signals and category analysis. It lists all metals, making the tool's scope unmistakable. This distinguishes it from sibling tools like agricultural_commodities or energy_markets.

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 industrial metal price data but does not explicitly tell when to use it versus alternatives. No when-not guidance is provided, but the context is clear enough for basic 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?

Without annotations, the description carries the full burden. It describes output fields and provides interpretation hints, but does not disclose potential limitations such as historical depth, rate limits, or pagination behavior. More detail on data range or update frequency would improve 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 concise at two sentences, front-loading the core purpose and output fields. The extra guidance is relevant and not verbose. Every sentence earns its place 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 simple single-parameter tool and the presence of an output schema, the description covers purpose, output details, and usage context thoroughly. It is complete enough for an agent to select and 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?

The input schema has only one parameter (ticker) with no description. The description adds valuable context by specifying that it expects a US stock ticker, which compensates for the 0% schema coverage. However, it does not specify format or case sensitivity.

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 SEC Form 4 insider trading activity for any US stock ticker, listing specific fields like insider name, role, transaction type, etc. This is a specific verb+resource combination that leaves no ambiguity about the tool's purpose.

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 guidance by interpreting insider buying clusters as bullish and selling before earnings as a red flag. It also suggests pairing with equity_analysis() and news_sentiment(). However, it does not explicitly state when not to use this tool or provide 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 provided, the description carries the burden of behavioral disclosure. It details the data returned, source, release frequency, and cost, but does not specify side effects or purely read-only behavior (though implied). More explicit disclaimers about non-modification would improve 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 information-dense and efficient, covering data points, interpretation, companions, source, and cost in a few sentences. It could be slightly more structured with bullet points, but it remains clear 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 fully covers the tool's output without relying on the output schema (though it exists). It lists all major data points and the qualitative phase. It also provides source, release frequency, cost, and companion tools, making it self-contained 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?

The input schema has zero parameters, so schema description coverage is 100%. The description add no value beyond the schema, but baseline for zero parameters is 4. There is no need to explain non-existent 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 explicitly states the tool returns specific labor-market signals including unemployment rates, payrolls, wage growth, labor-force participation, JOLTS data, and a plain-English labor phase. It distinguishes itself from siblings by naming companion tools (MacroPulse, ConsumerPulse, CyclePulse) and focuses on the Fed's dual mandate.

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 says to use it to gauge whether the US labor market is tightening or loosening, linking to the Fed's mandate. It mentions companion tools like MacroPulse, ConsumerPulse, CyclePulse, suggesting alternative contexts, though it does not explicitly state when not to use this tool.

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

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

No annotations are provided, so the description carries full burden. It explains key outputs like argentina_blue_premium_pct and its crisis threshold (>100%). It does not disclose data freshness or update frequency, but for a read-only intelligence tool, the behavioral disclosure 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?

Two concise sentences: one for purpose, one for content and use cases. No redundant information, and key details are front-loaded.

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

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

For a zero-parameter tool with an output schema, the description covers the main outputs and their significance. It lacks mention of data source or update cycle, but completeness is high given the simplicity.

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

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

The tool has zero parameters, and schema coverage is 100%. The description adds value by explaining the meaning of outputs, which compensates for the lack of parameter docs.

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

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

The description clearly identifies the tool as providing Latin American economic intelligence, listing specific currencies and commodity context. It distinguishes from siblings like macro_indicators and agricultural_commodities by focusing on LatAm specific rates and crisis signals.

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

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

Explicit usage contexts are given: 'Use for EM FX exposure, Argentina crisis monitoring, or commodity supply chain analysis.' No exclusions or alternatives are mentioned, but the guidance is clear and actionable.

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

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

No annotations are given, so the description carries full burden. It does not disclose data freshness, pagination, access limits, or whether operations are read-only. The behavioral scope 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?

The description is extremely concise, consisting of three short phrases. It is front-loaded with key terms and contains no extraneous 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?

Given the complexity of the domain (GOM leases) and poor parameter documentation, the description is insufficient. An agent lacks essential context to invoke the tool correctly, even with 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?

The input schema has three parameters (area, limit, status) with 0% description coverage. The tool description does not explain their meaning, valid values, or expected usage. An agent cannot infer 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 identifies the domain (Gulf of Mexico oil & gas), data source (BOEM), and key features (lease intelligence, block status, upcoming auction). However, it lacks an action verb (e.g., 'query', 'search') to explicitly state the tool's function.

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 siblings or what prerequisites exist. The description does not mention alternatives or 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?

Since no annotations exist, the description carries full burden. It transparently describes the output (signal states, volumes, events, zones) and its advantage over other metrics. However, it could mention data freshness or any limitations.

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 (5 sentences) and front-loaded with the main purpose. Each sentence provides unique value: assets, signals, metrics, usage guidance, and differentiation. No repetition or fluff.

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

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

Given the tool has no parameters, a rich output schema (implied), and the description covers output types, usage context, and signal strength, it is complete and sufficient for an agent to understand and select the tool.

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

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

With zero parameters and 100% schema coverage, the description is not required to add parameter info. It appropriately explains the tool's behavior and output, which is the baseline for no-param tools.

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

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

The description specifies the tool provides perp liquidation data for major assets, with signal states and metrics like volume and zones. It clearly distinguishes the tool from siblings like funding_rates and open_interest.

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 suggests pairing with funding_rates and open_interest for a complete picture, and notes its higher signal value. It lacks explicit when-not-to-use or comparison with all siblings (e.g., cascade_watch), but provides clear 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 provided, so description carries burden. It lists output indicators but lacks details on data freshness, caching, latency, or frequency. Assumed read-only, but not explicitly 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?

Two sentences, front-loaded with purpose. Every sentence adds value. 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 parameters and an output schema, the description adequately explains outputs and usage. Lacks behavioral context like data update frequency, 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?

No parameters in schema (100% coverage). Description adds value by explaining each output field's meaning and interpretation (e.g., yield curve spread negative = recession signal).

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 a US macroeconomic regime snapshot with specific indicators. Verb 'returns' is precise. Distinguishes from sibling tools like equity_analysis and portfolio_risk by focusing on macro conditions.

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 to use for assessing risk-on/risk-off positioning and pairs well with equity_analysis and portfolio_risk. Provides context but no exclusions or when-not guidance.

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

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

With no annotations provided, the description carries full burden. It discloses output format (severity-graded report with root cause analysis and remediation), pricing ($2.00 via x402), and the AI model used. It also lists detected vulnerability patterns, providing good transparency into tool behavior.

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

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

The description is concise (around 100 words) and well-structured. It front-loads the core purpose (Move audit powered by CopperheadAI), then lists supported chains and vulnerability types, and ends with input format and pricing. 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 tool's complexity and the presence of an output schema, the description adequately covers inputs, process, output format, and cost. It addresses the specific Move security context and lists relevant vulnerability categories, making it complete for an AI agent to understand and invoke correctly.

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

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

Schema description coverage is 0%, so the description adds needed context. It explains that 'source' and 'github_url' are alternative inputs for code, but 'contract_name' is not elaborated. Baseline compensation is partial; not all parameters gain meaning from the 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 performs a Move smart contract security audit, specifying blockchains (Aptos, Sui), vulnerability types (resource leaks, signer abuse, etc.), and differentiates from sibling tools like 'smart_contract_audit' and 'rust_contract_audit' by focusing on the Move VM and object model.

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 the user to provide raw Move source code or a GitHub URL, giving clear input guidance. It implies the tool is for Move contracts, but lacks explicit when-to-use or when-not-to-use guidance relative to siblings. However, the specialization is evident from the name and content.

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 the full burden. It notes 'Cached 5 min,' indicating data freshness and potential staleness. As a read-only scan tool, it does not require disclosure of destructive actions or authentication needs beyond what is typical. The caching detail adds value beyond a bare description.

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 front-loads the core purpose and outputs, followed by a caching note. No extraneous content; every word earns its place. It is optimally concise for an agent to quickly understand the tool's function.

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 low complexity (one required parameter, output schema present), the description covers the essential aspects: timeframe range, output fields, and caching behavior. It could elaborate on the interpretation of 'confluence_score' or 'bull/bear breakdown,' but the output schema likely provides structure. The description is complete enough for a scan 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 has 0% description coverage for the single 'symbol' parameter, and the description does not explicitly define 'symbol.' However, the parameter is inherently clear (a ticker symbol), and the output schema exists to clarify results. The description adds no additional semantic value, but the simplicity of the tool mitigates 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 states the tool provides multi-timeframe technical analysis confluence across specified timeframes (15m/1h/4h/1d) and lists the output fields (overall_signal, confluence_score, bull/bear breakdown, AI narrative). This distinguishes it from siblings that may focus on single timeframes or different asset classes.

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 multi-timeframe TA analysis but provides no explicit guidance on when to use this tool versus alternatives (e.g., 'tech_analysis') or when not to use it. The context suggests it is for obtaining a consolidated view, but no exclusions or conditions are stated.

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

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

No annotations provided, so description carries full burden. It discloses real-time nature, return fields with format, and auto-routing for crypto queries. Lacks details on rate limits or required permissions, but adequate for a read-only lookup.

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?

Four sentences, each serving a purpose: core function, behavioral trait, usage, and cross-tool coordination. Front-loaded with key information, no fluff.

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

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

With one required parameter and an output schema present, the description covers the input, output fields, and usage context. The auto-routing detail adds completeness. No gaps for this complexity level.

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 has only a string parameter with 0% coverage. The description adds meaning by specifying it accepts stock tickers or crypto assets and mentions crypto routing. Format (e.g., symbol) could be clearer, but sufficient for 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 real-time news sentiment for stock tickers or crypto assets, listing the specific outputs. It distinguishes from siblings by suggesting pairing with equity_analysis, tech_analysis, and insider_trading, implying different uses.

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 before a trade to detect sentiment regime or monitor news flow. Mentions pairing with other tools, but does not explain when NOT to use it or exclude cases.

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 describes outputs (USD totals, per-exchange breakdown, delta, dominant exchange) but does not disclose behavioral traits like rate limits, authentication needs, data freshness, or error handling. It is moderately transparent but lacks depth on behaviors.

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

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

The description is three sentences, front-loaded with a clear purpose, and uses formatting (bold, line breaks) for readability. 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?

For a zero-parameter tool with an output schema, the description is complete. It details the assets, exchanges, signals, and output fields, and even suggests pairing with a sibling tool. No missing context is apparent.

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

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

There are no parameters, so baseline is 4. The description adds context about what the tool returns (signals, breakdown) but does not need to explain parameters as there are none. Satisfies the baseline.

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

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

The description clearly states it provides perpetual futures open interest across multiple exchanges and assets, with specific signals and output breakdown. It uses specific verbs ('Returns', 'Pairs with') and distinguishes its focus on open interest from siblings like funding_rates, which is mentioned as complementary.

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 open interest and positioning signals, and explicitly pairs with funding_rates() for a complete picture. However, it does not provide explicit when-to-use vs alternatives or when-not-to-use guidance, leaving some ambiguity.

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 does so by detailing returned data and performance (crypto under 1s, stocks cached 5 min). It does not mention read-only nature or auth, but the context is sufficient given the tool's purpose.

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 with no filler. The first sentence states coverage, the second lists outputs and performance. Every word adds value, making it highly efficient and easy 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 the complexity and presence of an output schema, the description covers key aspects: coverage, outputs, and performance. It lacks explicit parameter format guidance and doesn't explain interpretation of signals, but the output schema likely handles return values.

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 0%, so the description must elaborate on the 'ticker' parameter. It only gives examples (BTC/ETH/SOL/AVAX) without specifying exact format (e.g., ticker symbol vs full name). This leaves ambiguity, making it inadequate for proper tool invocation.

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 options flow for stocks and specific cryptos via Deribit, and lists the returned signals and metrics. It distinguishes itself from siblings by covering both assets and mentioning performance differences, making its purpose very 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 implies use for options market sentiment on stocks or listed cryptos. It provides examples (BTC/ETH/SOL/AVAX) and notes caching differences, giving good context. However, it does not explicitly state when not to use it or mention alternative tools, though no obvious siblings exist.

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 states the tool converts PDFs to Markdown, implying a read-like operation, but does not disclose behavioral traits such as file size limits, handling of scanned PDFs, or whether the PDF is stored temporarily. This is adequate but could be more explicit.

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 with front-loaded action. It efficiently states the primary function, lists outputs, and provides use cases without 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 presence of an output schema (not shown but noted), the description adequately covers the tool's purpose and outputs. It mentions return fields and use cases but lacks details on constraints (e.g., max file size). Still, it is largely complete for a simple 2-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?

The schema has 0% description coverage, so the description must explain parameters. It clarifies that 'url' is a PDF URL, but does not explicitly describe the 'summarize' boolean parameter, though the output list mentions an AI summary. This partially compensates but leaves room for improvement.

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 'Convert any PDF document (via URL) to clean Markdown,' clearly stating the verb and resource. It lists specific outputs (markdown text, page count, etc.) and use cases (whitepapers, reports), making the purpose unambiguous and distinct from unrelated 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 suggests usage for 'whitepapers, reports, contracts, or research papers,' providing clear context. However, it does not explicitly state when not to use the tool (e.g., for local files) or mention alternatives. With no directly similar siblings, this is a minor gap.

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 disclose behavioral traits. It only says 'analysis' (implying a read operation) without stating side effects, auth needs, or output nature. Minimal disclosure.

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: first establishes purpose, second gives precise input format. No wasted words, front-loaded, and easy 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?

Output schema exists, so return value details are not needed. The description covers the single parameter and its formatting. For a simple tool, this is sufficient; could briefly mention output type for extra clarity.

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 0%, but the description adds critical value by specifying the exact format: 'comma-separated string' with example 'AAPL,MSFT,GOOGL'. This goes beyond the schema's type 'string'.

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 the tool performs 'portfolio risk analysis' with specific aspects (concentration, volatility, correlation). However, it does not differentiate from sibling tools like 'equity_analysis' or 'defi_risk', so it loses a point.

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

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

Provides an explicit format instruction for the tickers parameter ('comma-separated string'). But lacks guidance on when to use this tool versus alternatives or when not to use it; usage is only 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 lists the data content but fails to disclose behavioral traits such as data freshness, update frequency, or whether it is read-only. It does not contradict expectations, but lacks depth for a tool that returns data.

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 single sentence is perfectly concise, front-loading the tool's purpose and listing all key data points 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 that an output schema exists, the description does not need to detail return values. It sufficiently covers the scope of the tool (US real estate market metrics) and is complete for a simple, parameterless 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?

The tool has zero parameters, so by rule baseline is 4. The description does not need to add parameter semantics, and the listing of metrics provides sufficient context for the no-parameter interface.

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 provides US real estate market data, listing specific metrics (mortgage rates, housing starts, etc.). It is a specific verb+resource that distinguishes it from sibling tools like 'macro_indicators' or 'energy_markets'.

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 accessing US real estate data, but does not provide explicit when-to-use or when-not-to-use guidance or alternatives. Sibling tool names hint at broader categories, but no direct comparison 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?

No annotations are provided, so the description carries full burden. It describes the action (auto-detects framework, applies checks, returns a report) and notes the cost. However, it does not disclose important behavioral traits like data handling/privacy (submitted code is sent to CottonmouthAI), required permissions, or any rate limits. The description is partially transparent but has 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 two sentences plus a pricing note, all front-loaded. The first sentence states purpose and frameworks, the second details checks and output. Every sentence adds value, 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's complexity (multi-framework, security checks, output schema) and the presence of an output schema (which covers return values), the description is fairly complete. It covers purpose, inputs, checks, output format, and cost. Minor omissions include error handling or input size limits, but overall adequate.

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 0%, so the description must explain parameters. It mentions providing 'raw Rust source code or a GitHub URL', which covers two parameters (source, github_url) but does not explain the 'contract_name' parameter (defaults to 'Contract'). The input schema has 3 parameters, so explanation is incomplete.

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 a Rust smart contract security audit, lists supported frameworks (CosmWasm, Anchor/Solana, Stellar/Soroban, NEAR), and enumerates targeted checks. This distinguishes it from sibling tools like 'smart_contract_audit' and 'move_contract_audit' which likely target other languages.

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 specifies the input format (raw Rust source code or GitHub URL) and mentions the cost ($2.00 via x402). It implicitly indicates use for Rust contracts, but does not explicitly state when not to use or mention alternatives, such as using 'smart_contract_audit' for other languages.

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 two risk dimensions and supply/TVL context, and explicitly scopes its analysis to on-chain admin and liquidity risk only, excluding default probability, yield source, or legal terms. This is thorough for a read-only analysis 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 (2-3 sentences) and well-structured: it starts with the tool's purpose, then details what it returns, and ends with usage guidance. 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 that an output schema exists, the description does not need to detail return values. It adequately covers input parameters, usage context, scope, and limitations, making it 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?

The input schema has 0% description coverage, but the description adds significant meaning by explaining how to use the parameters: 'Pass vault=<id> such as midas-mtbill, or protocol=<name> such as midas.' This guides the agent on valid inputs beyond the schema's default empty strings.

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 provides per-vault risk profiles for tokenized RWA positions on Base, listing two specific risk dimensions (admin/freeze risk and exit-liquidity) plus supply/TVL context. It distinguishes itself from sibling tools by focusing on RWA-specific on-chain risks.

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 'Call before allocating capital into an RWA vault,' providing clear usage context. It also includes a scope note clarifying what risks are not covered. However, it does not mention specific alternative tools or when not to use this tool.

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

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

No annotations are provided, so the description bears full burden. It discloses the use of RattlerAI, Slither, cost ($2.00), and output format. It does not mention any destructive behavior or side effects, which is acceptable given the audit use case.

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 that is clear and front-loaded with the purpose. It is moderately concise but could be more structured (e.g., bullet points) without losing 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?

Given that an output schema exists, the description adequately covers the input (source code or URL), output (Code4rena-style report), use case, cost, and underlying tools. It does not explain all parameters or constraints like timeouts, but 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 0%. The description adds meaning by explaining that input can be Solidity source code or a GitHub URL, corresponding to the 'source' and 'github_url' parameters. However, the 'contract_name' parameter is not explained, and default values are not discussed.

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 performs a security audit on Solidity smart contracts, powered by RattlerAI. It lists specific vulnerability classes and distinguishes itself from sibling tools like move_contract_audit and rust_contract_audit by focusing on Solidity.

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: 'Ideal as a pre-deploy sanity check or audit triage.' It implies when to use but does not explicitly state when not to use or mention 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 full burden. It discloses the tool's behavior: monitoring peg, backing, mint/burn, and risk score. It also explains how the parameter affects the output (full report vs. single stablecoin). This is sufficient for a non-destructive read 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?

Two sentences with zero waste. The first front-loads the purpose and key metrics, the second explains parameter usage. Every word 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?

The tool has only one optional parameter and an output schema. The description covers the input behavior and key output facets sufficiently. The output schema (not shown) likely handles the return shape, so no further detail is 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?

Schema description coverage is 0%, so the description must compensate. It does so by specifying the symbol parameter expects one of four stablecoins (USDC/USDT/DAI/FRAX) or empty for a full report. This adds meaning beyond the raw schema, which only defines a string with no 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 starts with a clear verb+resource: 'Stablecoin stability monitoring'. It lists specific metrics (peg deviation, backing ratio, mint/burn activity, depeg risk score), making the purpose highly specific and distinct from sibling tools like 'defi_risk' or 'rwa_risk', which likely cover broader DeFi or real-world 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 tells the agent when to pass a symbol vs. leave empty: 'Pass symbol (USDC/USDT/DAI/FRAX) or leave empty for full report.' This provides clear usage guidance, though it does not explicitly state when not to use this tool (e.g., if you need non-stablecoin data), which is acceptable given the 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?

Discloses live data sources (DeFiLlama), cost ($0.05), and return fields. No annotations exist, but the description adequately conveys read-only behavior without 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?

Three sentences, each adding distinct value: purpose, return fields, and usage. No wasted words; front-loaded with 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 the single optional parameter and presence of an output schema, the description covers all necessary aspects: what returns (protocol APY, exchange rates, liquid staking, best strategy), filtering, and cost.

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?

Adds complete usage instructions for the sole parameter 'symbol': includes example values (ETH, SOL, ATOM) and clearly explains default behavior (blank for full report). This fully compensates for 0% schema description coverage.

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

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

The description uses specific verbs ('compare', 'returns') and resources ('staking yield comparison across 7 assets'), clearly distinguishing it from sibling tools that cover different financial 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?

Explicitly states 'Use when an agent needs to know where to stake an asset for maximum yield,' providing clear context. No exclusions or alternatives needed as no sibling tool covers staking yields.

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 source (USGS 2025), cost ($0.05), and that it is a query (no side effects). Could be improved by explicitly stating it is read-only, but overall 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?

Well-structured with a front-loaded summary, usage instructions, and source info. Slightly verbose in listing minerals, but informative without 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?

Covers all aspects: purpose, output details, usage, source, and cost. With an output schema present, explanation of return values is bonus. Thorough for a simple one-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?

The input schema has 0% description coverage, but the description fully explains the parameter 'commodity', including what to pass and behavior when omitted ('omit for leaderboard'). Adds essential meaning.

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

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

The description clearly states the tool returns 'supply-concentration & US import-reliance signal' for critical minerals, and lists examples. It differentiates itself from sibling tools like 'agricultural_commodities' by focusing on critical minerals.

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 it ('before a sourcing, policy, or investment decision') and how to invoke it ('Pass commodity=<mineral name>; omit for leaderboard'). No explicit alternatives, but purpose is distinct enough.

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 fully carries the burden. It reveals a GET request with a cost of $0.05, which is helpful, but does not disclose rate limits, authentication, or potential side effects. The tool is read-only by nature, but this is not explicitly stated. The description provides moderate 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 three sentences: a concise title, a list of return values, and an interpretive clue plus cost info. Every sentence adds value, and the most critical info (purpose and outputs) appears first. 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 zero parameters and the presence of an output schema, the description covers the core information: what the tool returns, a brief interpretation, and cost. It lacks details like update frequency or data source reliability, but the agent can likely decide to use it based on the provided info. Completeness is high but not maximal.

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

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

There are zero input parameters, so the schema coverage is trivially 100%. The description lists output fields but does not add meaning to input parameters (none exist). According to the rule, 0 parameters yields a baseline of 4. The description adds context about the output but is not required to elaborate on 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 it is a 'Global supply chain stress monitor' and enumerates specific outputs (stress_score, shipping rates, GSCPI, PPI, momentum signal, AI brief). This verb+resource combination is concrete and distinguishes it from sibling tools like agricultural_commodities or energy_markets which focus on different domains.

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 supply chain stress monitoring but does not explicitly state when to use this tool versus alternatives. The sentence 'High stress_score signals input cost pressure and delivery delays upstream of earnings' provides context for interpretation but lacks explicit guidance on exclusions or when not to 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 the full burden. It mentions a 5-minute cache but fails to disclose any potential destructive actions, authentication requirements, rate limits, or how the AI signal is generated. This is a significant gap for a tool that likely performs analysis.

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 state the core functionality, supported timeframes, and caching behavior. Every word earns its place, and the most important information (indicators + AI signal) comes first.

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 that an output schema exists (not shown), the description need not detail return values. However, it leaves ambiguity about whether all 18 indicators are always returned or only the AI signal. The caching refresh is mentioned, but no other contextual details (e.g., whether it works on all asset classes) are provided.

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

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

The input schema has 0% description coverage, so the description must add meaning. It lists the available timeframes (15m, 1h, 4h, 1d) and clarifies that 'symbol' is for any ticker, with a default timeframe of 1d. This adds value beyond the schema, though it does not explain the format of the symbol (e.g., 'AAPL' vs 'BTC-USD').

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 18 technical indicators plus an AI signal for any ticker, with specific timeframes. It distinguishes from many siblings in the list that focus on other domains (e.g., agricultural commodities, equity analysis). However, it doesn't explicitly differentiate from tools like 'multi_timeframe_scan' or 'news_sentiment' that might also be relevant for technical analysis.

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 use when needing technical indicators or AI signals for a ticker, but it provides no explicit guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. The agent must infer usage from the tool 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 bears full burden. It lists the checks performed but does not disclose whether the tool is read-only, if it requires API keys or incurs costs, or any rate limits. For a data-fetching tool, this lack of behavioral context is a significant gap.

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 tightly crafted sentences: the first defines the tool's output (checks), the second lists supported chains. Every word adds value with no redundancy. It is front-loaded with the core 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?

Given the presence of an output schema (not shown), the description need not detail return values. It covers the essential inputs (supported chains) and outputs (checks). For a tool with two parameters, the description is sufficiently complete, though it could mention the ERC-20 restriction more explicitly.

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

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

The input schema has 0% description coverage, so the description must compensate. It lists supported chains, giving context to the 'chain' parameter, but does not explain that 'chain' has a default of 'eth' or that 'contract_address' is the token address. The description adds moderate value beyond the schema but falls short of fully clarifying 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 it performs full ERC-20 token due diligence, listing specific checks (risk score, honeypot, liquidity, holder concentration, ownership). It also specifies supported chains, making the resource and verb explicit. This distinguishes it from siblings like contract_check which likely focus on contract code audits rather than token 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 implies usage for ERC-20 tokens on supported chains (eth, base, bsc, arb, poly). It does not explicitly state when not to use it or name alternatives, but the listed checks and supported chains provide clear context. A clearer exclusion statement would improve differentiation from tools like defi_risk or contract_check.

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 tool returns risk score, liquidity, deployer history, and launch metadata, which adds behavioral context. However, it does not mention side effects, permissions, or limitations (e.g., data freshness, supported networks), leaving 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?

Two concise, front-loaded sentences with zero wasted words. Every sentence conveys essential information about the tool's purpose and outputs.

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

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

Given the tool has no parameters and an output schema exists, the description is mostly complete. It explains the filtering logic and outputs. However, it lacks detail on what qualifies as 'newly launched' or data source frequency, which could be refined.

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

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

The input schema has no parameters (0 params, 100% coverage). The description does not add parameter info because none exist. Per calibration, baseline is 3 for high schema coverage, and the description does not need to compensate.

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 a specific verb ('Scan') and resource ('newly launched tokens'). It distinguishes from siblings by emphasizing filtering for legitimate launches vs. honeypots, which sets it apart from other crypto analysis 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 for screening new tokens and avoiding scams, but it lacks explicit guidance on when to use this tool versus alternatives (e.g., contract_check or token_due_diligence). No when-not-to-use or prerequisites 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 are provided, so the description must cover safety. It mentions the cost ($0.05 via x402) and public domain sources, but does not disclose any side effects, authentication needs, or rate limits. The read-only nature is implied but not explicit.

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?

Four sentences with front-loaded purpose, followed by parameter instruction and context (data sources, cost). Every sentence earns its place; 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 a single parameter and the presence of an output schema, the description is fairly complete. It explains the parameter usage, data sources, and cost. It could mention output size or pagination, but the information provided is sufficient for a simple tool.

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

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

With 0% schema coverage, the description adds significant meaning: it explains the parameter accepts commodity keywords or HS2 chapter codes, provides examples ('steel' or '85'), and implies usage. This compensates well for the sparse 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 returns US trade-flow and tariff signals by commodity category, listing examples and data sources. It mentions being a companion to supply-chain data but does not explicitly distinguish it from the many sibling tools that also provide economic 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 instructs to pass a category parameter with examples ('steel' or '85'), implying usage context. However, it does not provide explicit guidance on when not to use this tool or alternatives among the numerous 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?

Annotations are absent, so the description must convey behavior. It lists return fields but does not disclose side effects, authentication needs, rate limits, or destructive potential. It implies read-only analysis, which is adequate but not explicit.

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 efficiently lists key return items. It is concise and front-loaded, but could be slightly more structured (e.g., separating inputs from outputs).

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 an output schema exists (signal true), the description covers return values adequately. However, it lacks parameter explanations and usage context, making it partially incomplete for complex use cases.

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 0%, and the description provides no explanation for parameters (wallet, days). It adds no meaning beyond the parameter names and types 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 clearly states it is an on-chain wallet PnL analyzer for Base, lists specific return values (gains, portfolio value, win rate, holdings, verdict), and distinguishes from siblings like wallet_risk by focusing on profit analysis.

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, no when-not-to-use or prerequisite information. The description only states what it does without context for 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 full burden. It discloses output fields (risk_score, sanctions_hit, risk_flags, etc.) and implies a read-only operation. However, it does not mention data sources, freshness, rate limits, or any authorization requirements, leaving some uncertainty about behavior.

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

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

The description is concise with three short sentences. The first sentence states the core purpose, the second lists key outputs, and the third provides usage guidance. 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 an output schema exists, the description does not need to detail return values, but it does so helpfully. However, it omits context about the chain parameter (possible values, supported networks) and any limitations (e.g., on-chain lookup cost). This leaves some gaps for a risk assessment 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 0%, so the description must compensate. It explains the 'address' parameter implicitly by mentioning 'any Ethereum address,' but it completely ignores the 'chain' parameter (type string, default 'eth'), leaving its purpose unclear. This is a significant 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 states it returns a wallet risk score (0-10) for any Ethereum address and lists specific return fields. The use case is explicitly stated: 'Use before transacting with an unknown counterparty or screening a wallet for compliance,' which differentiates it from sibling tools like wallet_pnl or defi_risk.

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 when-to-use guidance ('Use before transacting with an unknown counterparty or screening a wallet for compliance'). However, it does not mention when not to use this tool or suggest alternatives among the many siblings, which would be helpful.

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 burdens behavior entirely. It discloses auto-fetching, valuation, and output types (risk score, narrative, flags), but omits details like data freshness, authentication needs, error handling, or rate limits. Somewhat transparent but incomplete.

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

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

The description is three sentences, efficient and front-loaded with the core purpose. However, the second and third sentences are somewhat run-on, but still concise overall.

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 0 required parameters and an output schema (not shown), the description covers inputs, process, and outputs adequately. However, it lacks usage guidelines and parameter details, and does not differentiate from overlapping siblings, leaving gaps for an AI agent.

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

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

Schema coverage is 0%, and the description only names parameters (wallet, tickers, contracts) without specifying format, examples, combination rules, or constraints. It adds minimal meaning beyond the schema defaults, failing to compensate for the lack of schema 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 it is a 'Cross-asset portfolio risk analyzer' and details what it does: accepts wallet address, fetches Base on-chain holdings, values positions, and returns risk score, narrative, and flags. This uniquely distinguishes it from siblings like 'portfolio_risk' or 'wallet_risk' by specifying cross-asset and on-chain focus.

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 inputs (wallet, tickers, contracts) but does not provide explicit guidance on when to use this tool versus alternatives like 'portfolio_risk' or 'wallet_risk'. No when-not or selection criteria are given, leaving the agent to infer 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 discloses behavioral traits: probability calculation method (empirical vs blended Gumbel), 'method_divergence' logic for forcing 'PASS', signal values, outlier identification, coordinate alignment, and cost. This is highly 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 dense with information but not overly long. It is front-loaded with the main output type. It could be more structured (e.g., bullet points) for easier scanning, but every sentence is 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 the complexity of weather probability forecasts, the description covers key aspects: ensemble details, probability types, signal logic, and cost. Some technical terms like 'method_divergence' and 'PASS' could use more explanation, but the presence of an output schema likely fills 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 coverage is 0%, so the description must compensate. It explains 'direction' (greater/less), lists 10 valid cities, mentions 'threshold' (but not type), and implies 'date' is optional. It adds significant meaning beyond the bare schema, though date format could be clarified.

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 the tool computes weather probability using a 7-model consensus and 80 ensemble members. It explicitly states the output includes probability, signal, divergence, and outlier, distinguishing it from sibling tools that are mostly financial or audit-related.

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 when to use the tool (weather forecasting) and explains the 'direction' parameter. However, it does not explicitly mention when not to use it or compare to alternatives, though sibling tools are so different that confusion is unlikely.

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 disclose behavioral traits. It states the tool 'returns list' implying read-only, but does not discuss data latency, rate limits, pagination, authentication, or any limitations. The description is adequate but not thorough in revealing how the tool behaves beyond its basic output.

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

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

The description is three sentences long, with the first sentence stating the core purpose, the second detailing output, and the third providing usage guidance. Every sentence adds value; there is no redundancy or fluff.

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

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

Given the tool has only one optional parameter and an output schema (not visible but referenced), the description covers purpose, specific chains, output fields, and usage scenario. It is complete enough for an agent to invoke correctly, though missing details like data freshness or support for additional chains beyond the two named.

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 min_usd is described in the description with its purpose ('set threshold') and default value ($1M). The input schema provides type and default but no description; thus the description fully compensates by adding context that meaningfully aids parameter use.

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 provides real-time whale transfer alerts on Base and Ethereum, listing returned fields (sender, receiver, token, amount, USD value). This clearly defines the tool's function and distinguishes it from siblings like chainscout_intelligence, which may offer different on-chain 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 advises using the tool 'to detect smart money movements or monitor an ecosystem for unusual capital flows,' giving clear context for when to use it. It also explains the optional parameter min_usd for setting thresholds. However, it does not mention when not to use it 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.