x402-endpoints

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

The description reveals the report is composed from live public web signals and includes a signed receipt and price per call. However, it does not disclose whether the tool is read-only, any rate limits, or authentication needs beyond payment. No annotations exist to compensate.

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 containing all key information (purpose, outputs, pricing, payment method). It is dense but not overly long; could be slightly improved with structuring but remains 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 lack of output schema, the description comprehensively lists output components (score, rating, recommendation, etc.). It provides context on pricing and payment. However, it lacks explicit differentiation from sibling analysis tools.

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?

Both parameters have schema descriptions that cover 100% of the parameters. The description adds examples (e.g., 'stripe.com') and lists focus options, but this is minor additional value beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states the tool produces a structured analysis report with specific outputs (positioning, strengths, risks, etc.) for any URL, company, product, or subject. It distinguishes itself from siblings like agent_due_diligence by mentioning a fixed schema and live web 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?

The description implies usage for competitive, investment, or partnership analysis but does not explicitly state when to use this tool versus alternatives like agent_visibility_audit or agent_due_diligence. No 'when not to use' guidance is provided.

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

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

No annotations are provided, so the description carries full responsibility. It thoroughly discloses the tool's behavior: performs risk assessment, reversibility check, timing, outputs a verdict (CLEAR/LIMIT/REVIEW/BLOCK), and produces a cryptographically signed ClearancePacket with details. It also mentions pricing and payment method (x402). This is comprehensive.

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

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

The description is front-loaded with essential purpose and usage information ('Safety preflight before...'). It includes pricing and a concise summary. While slightly lengthy, every sentence adds value. Could be tightened slightly but overall efficient.

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

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

Given no annotations or output schema, the description effectively explains the tool's output (ClearancePacket with decision, approved amount, policy version, etc.). It covers when to use and behavioral traits. It lacks details on authentication prerequisites but is otherwise complete for the tool's complexity.

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

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

Schema coverage is 100% with adequate parameter descriptions. The tool description adds no additional semantic value beyond what the schema already provides (e.g., action, target, context, amount_usd, reversible, action_type). Baseline applies; no extra enrichment.

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

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

The description clearly identifies the tool as a 'Safety preflight' for destructive/costly actions, listing specific verbs like delete, deploy, transfer funds, etc. It distinguishes from siblings like agent_clearance_packet by stating it provides a cryptographically signed ClearancePacket as proof of authorization, and calls itself an 'Agent action guardrail / clearance / human-in-the-loop gate'.

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

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

The description explicitly states when to use the tool: 'before an agent runs a DESTRUCTIVE, costly or IRREVERSIBLE action' with examples. It implies when not to use (for non-critical actions) but does not explicitly name alternative tools. 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?

With no annotations, the description fully bears the transparency burden. It discloses the paid nature ($1.50, x402), return format (verdict, amounts, expiry, Ed25519 signature), and offline verifiability. It does not discuss failure modes or rate limits, but the disclosed traits are detailed.

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 repetitive and verbose. The first sentence is very long, and information is duplicated (e.g., the description of the clearance packet appears twice). It could be condensed by at least half without losing meaning.

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

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

Given no output schema, the description thoroughly explains the return value (verdict, amounts, expiry, signature) and input parameters. It also includes cost, payment method, and verification capability. This is fully adequate for an agent to understand and invoke the tool correctly.

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

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

Schema coverage is 100% with descriptions for all three parameters. The description adds clarity by explaining 'depth' as forensics graph hops with a default value, and lists the parameters in context. This goes beyond the schema's minimal descriptions.

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

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

The description clearly states the tool provides a signed clearance packet for pre-payment AML/KYT checks, combining multiple screenings into a verdict. However, it doesn't explicitly differentiate from the sibling 'agent_clearance' tool, so purpose clarity is strong but not perfect.

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 when to use the tool ('Can I send this capital to THIS wallet?', pre-payment clearance) and includes cost/payment details. However, it lacks guidance on when not to use it or how it compares to alternatives like 'agent_clearance' or 'agent_due_diligence'.

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 thoroughly discloses what the tool checks (prompt-injection, data exfiltration, dangerous code, hidden Unicode, instruction overrides), output format (risk score 0-100, SAFE/WARN/BLOCK verdict, structured findings), pricing, and performance characteristics (fast, cheap, deterministic, high-volume).

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

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

The description is well-structured with two main sentences followed by a list of threats and a pricing note. It is front-loaded with the core purpose and action. While packed with useful information, it could be slightly more concise by grouping some details, but it is not wasteful.

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 (2 params, no output schema), the description covers all essential aspects: purpose, input, output format, pricing, and performance. It explains the output (risk score, verdict, findings) sufficiently for an AI agent to invoke and interpret results.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining that 'content' is raw data to scan before ingestion and that 'source_type' is optional with example values (skill, webpage, user_input, tool_output, document). This context enriches the schema's brief descriptions.

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

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

The description clearly states the tool scans external content for security threats (prompt-injection, data exfiltration, etc.) before ingestion. It uses specific verbs ('scan') and resources ('external content'), and distinguishes itself from sibling tools focused on other security/verification tasks.

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 'before an agent INGESTS it' and lists content types (SKILL.md, web page, user input, tool output), providing clear usage context. However, it does not explicitly state when not to use it or mention alternatives, leaving minor room for improvement.

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

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

Thoroughly describes the output components (risk dossier, signals, score, verdict, recommendation, signed receipt) and mentions pricing and payment method ($0.50 per call, x402 USDC on Base). No annotations exist, so the description carries full burden and does it well.

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?

Every sentence adds value: purpose, output breakdown, use cases, pricing. Front-loaded with the core action and outcome. Not overly verbose.

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

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

Explains return values in detail despite no output schema. Could be more structured (e.g., mention JSON format), but sufficiently complete for a one-call due diligence 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 covers all 3 parameters with descriptions. The tool description adds examples for target and optional context/target_type but does not add new semantic meaning beyond what the schema provides. Baseline 3 is appropriate.

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

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

Clearly states the tool vets entities (company, crypto project, counterparty, domain) and produces a risk dossier with synthesis, signals, risk score, verdict, and recommendation. Specifically distinguishes from siblings by focusing on due diligence and replacing manual searches.

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 'vet before engaging' and describes what the tool replaces. However, it does not provide when-not-to-use or compare with sibling tools that may overlap (e.g., sanctions_screen, crypto_token_safety).

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 alone covers behavioral traits. It discloses the input requirements, output structure (e.g., revenue, expenses, net), pricing, and payment method. However, it does not mention potential errors, read-only nature, or side effects. Lacks full transparency for a tool with no annotations.

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

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

The description is somewhat repetitive (e.g., 'Your AI agent's books in one call' appears twice, and the value proposition is repeated). Could be more concise without losing 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 simplicity (2 parameters, no output schema), the description thoroughly covers what the tool does, what it returns, and the pricing context. The agent can fully understand the tool's output without needing additional schema.

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

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

Schema coverage is 100%, and the description adds meaningful context beyond the schema: it explains the period parameter values ('7d/30d/90d') and that the wallet is an EVM address on Base. This enhances understanding.

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

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

The description clearly states the tool's purpose: structured USDC accounting for a wallet on Base, including revenue vs expenses, net, transaction count, top counterparties, and weekly breakdown. It differentiates from sibling crypto tools by focusing specifically on USDC accounting with a 'turnkey bookkeeping' angle.

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

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

The description explains when to use it (e.g., for structured accounting reports) and distinguishes its value ('the value is the structuring, not raw data access'). It does not explicitly contrast with siblings or state when not to use, but the context is clear.

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

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

No annotations are provided, so the description carries the full burden. It discloses that the tool scores, rates, suggests, and rewrites, and also mentions the cost per call ($0.10) and payment method. This provides a clear behavioral picture, though it does not explicitly state any side effects or 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 packed with useful information and is well-structured, starting with the main purpose. It is slightly longer than minimal but every sentence adds value. It could be trimmed slightly without losing meaning, but overall it is effective.

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

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

Given no output schema, the description explicitly details what the output contains: a multi-criteria scorecard, rating, top suggestions, and an improved rewrite. All parameters are covered, and the description addresses the tool's complexity fully, making it ready for agent use.

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

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

The input schema has 100% description coverage for the three parameters. The description adds context by specifying the types of text (email, social post, customer reply) and the optional goal and format parameters, which goes beyond the schema's brief descriptions. This adds meaningful value for agent selection.

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: reviewing and improving agent outbound text before sending. It lists specific criteria (clarity, spam-safety, tone, etc.) and outcomes (scorecard, rating, suggestions, rewrite). This specificity distinguishes it from sibling tools such as agent_content_scan or agent_analysis_report, which likely have different scopes.

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 any outbound text from an agent (email, social post, customer reply) and is clear about the context. However, it does not explicitly state when not to use this tool or compare it to alternative tools, leaving room for 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 fully carries the burden. It discloses that the tool reads on-chain data, computes various metrics (owner agent-farming, footprint-less reviewers, etc.), returns a signed offline-verifiable verdict, and requires payment of $1.00 USDC on Base mainnet. No destructive actions mentioned.

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 overly verbose and repetitive, with the second paragraph largely duplicating the first. It could be significantly shortened without loss of 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?

Despite lacking an output schema, the description explains the return value (delta + signed verdict) and enumerates the reputation components. It also covers pricing and payment method. Some structure of the verdict could be clearer.

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

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

Schema coverage is 100% with both parameters described. The description adds no additional parameter semantics beyond the schema; it simply restates the options.

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 reads on-chain ERC-8004 registries, computes declared and measured reputation, and returns a delta with a signed verdict. It distinguishes from sibling tools by emphasizing Sybil-correction and audit-grade 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 gives input requirements (agent_id or wallet) and mentions pricing ($1.00 x402 payment). It implies usage for reputation due-diligence, but lacks explicit when-not-to-use or alternatives compared to sibling tools like agent_clearance.

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 behavioral traits. It mentions the call is cheap and frequent (suggesting read-only safety), outlines the output conceptually, and gives cost details. However, it does not explicitly state safety (e.g., no side effects), nor describe error behavior or response format beyond a high-level summary.

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 highly repetitive, containing two nearly identical paragraphs that restate the same purpose and features. Essential information could be conveyed in one concise paragraph, as the current version wastes space with redundancy (e.g., the same phrase appears multiple times).

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 one parameter and no output schema. The description covers purpose, outputs, pricing, and references to a related tool, but does not explain the return structure, error handling, or what happens when the seller is not found. For a simple tool, it provides adequate context but lacks full coverage of all possible scenarios.

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

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

Schema coverage is 100% with a single parameter 'seller' documented in the schema. The description redundantly restates the schema info ('wallet or origin domain') without adding new semantics like allowed formats or examples beyond what the schema already provides.

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 'quick keyword-relevance rank of an x402 seller in CDP Bazaar discovery' and explicitly distinguishes it from 'raw settled-volume rank' shown by free explorers. It also specifies outputs ('best rank + per-category-keyword rank') and differentiates from sibling tools like agent_visibility_audit by referencing it as a deeper alternative.

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 this tool as 'the frequent pulse for monitoring x402 discoverability' and points to the full visibility-audit when rank slips, implying when to switch tools. It also notes pricing ($0.10 per call) and payment method, but lacks explicit 'when not to use' or a direct comparison to other sibling tools.

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

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

No annotations provided, so description must fully disclose. It mentions the output includes a signed snapshot, payment requirement ($1 USDC), and that it is a discovery audit. It does not contradict safety assumptions. Additional context like Ed25519 signature and payment clarifies usage constraints.

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 repetitive, essentially stating the same information twice with the same level of detail. It could be condensed to a single paragraph without losing meaning. The key points are front-loaded, but redundancy harms conciseness.

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

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

Given the tool's complexity and lack of output schema, the description covers all major components: registries, types of scores, benchmark, fixes, delta, and payment. It provides enough context for an agent to understand what the audit returns and how it works.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds value by explaining how to use the snapshot parameter ('optional signed snapshot from previous audit') and clarifying the seller parameter format. This goes beyond the schema's descriptions.

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

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

The description clearly states that it audits discoverability of x402 agents across specific registries (CDP Bazaar, 402index), with specific outputs like keyword-relevance rank, metadata-quality score, and top-3 benchmark. It distinguishes itself from related tools like agent_rank_check by focusing on relevance rank not raw volume rank.

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 implicitly tells when to use it via the question 'Why am I not being found?' and explains what it does vs what it doesn't (not raw settled-volume rank). However, it does not explicitly list sibling alternatives or 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 exist, so the description carries full burden. It discloses return fields (type, family, date, court, SIREN, link), price ($0.01 per call), payment method (USDC on Base mainnet), and source (official DILA). No contradictions or missing critical 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 somewhat verbose, mixing pricing, use cases, and return details. While all information is relevant, it could be more structured with bullet points or shorter sentences for easier parsing.

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

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

Given no output schema, the description adequately covers return values and input parameters. It also provides pricing, use cases, and source credibility. Missing rate limits or error handling, but not critical for a paid API.

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

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

Schema coverage is 100%, and the description adds value beyond the schema: provides input examples (e.g., 'OVH'), clarifies limit range (1-100), and lists filter options (creation, modification, etc.). Enhances usability.

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

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

The description clearly states it searches the French BODACC registry for legal announcements, specifying types (incorporations, modifications, radiations, insolvencies), coverage (France, by name/SIREN/RCS), and use cases (credit-risk, KYB). This distinguishes it from siblings like fr_sirene_lookup and fr_legifrance_search.

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 input examples and mentions use cases (credit-risk, KYB, AML), but does not explicitly state when to use this tool vs. alternatives or when not to use it. No direct comparison with sibling tools.

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

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

With no annotations, the description carries full burden. It discloses read-only behavior (queries logs), pricing ($0.05/call via x402), block span cap, and that unknown signature topics are returned raw. However, it does not mention retry behavior, error handling, or rate limits.

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

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

The description is repetitive (e.g., nearly identical opening sentences), includes pricing in the middle of the function description, and is overly long. Could be trimmed to one clear paragraph.

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 main features (supported events, filtering, block range, pricing) but lacks details about the output format (structure of decoded events, pagination, or how to handle raw topics). Since there is no output schema, more guidance on return values 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 has 100% coverage, baseline 3. Description adds context: lists example event names, explains the relationship between from_block, to_block, and lookback, and gives default values. This adds meaning beyond the schema's terse descriptions.

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

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

The description clearly states it queries decoded on-chain event logs from a contract on Base, filtering by event name/signature/block range, and explicitly lists supported event types. It distinguishes from sibling blockchain tools (e.g., crypto_token_dossier) by focusing on raw event logs rather than token metadata or safety.

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 is for querying on-chain events, but no explicit guidance on when to use this tool versus related tools like crypto_wallet_xray or solana_token_safety. No exclusion criteria or alternatives mentioned.

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

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

No annotations provided, so description bears full burden. It discloses derivation type (heuristic), non-official rating, deterministic behavior, pricing ($0.05 per call via x402), and dataset limitations. Lacks details on error handling or caching but covers key behavioral aspects beyond basic read/write.

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

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

Purpose is front-loaded, but the description is repetitive, stating 'Derived/heuristic, not an official rating' and 'single high-emissions pathway' twice. Could be tightened without losing clarity.

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

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

Given no output schema, the description adequately explains what is returned (composite score, per-hazard subscores, baseline comparison, methodology) and includes pricing and deterministic nature. Lacks explicit output field names but covers high-level completeness for a derived score 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?

All 4 parameters are documented in the input schema (100% coverage), so baseline is 3. The description adds context: horizon range (2030-2050), example values for lat/lon, and scenario options as 'informational'. This is marginal additional value beyond schema descriptions.

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

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

Clearly states it derives a composite climate risk score from Open-Meteo CMIP6 projections, specifying hazards (heat/drought/extreme-rain), range (0-100), inputs (coordinate, scenario), and comparison type (baseline vs future). Distinguishes from siblings by describing its unique purpose and application 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?

Explicitly lists intended use cases (property due-diligence, ESG, parametric-insurance, siting) and notes limitations (single high-emissions pathway, heuristic nature, scenario informational). Provides scenario options and horizon range. Does not explicitly state when not to use, but limitations imply appropriate use 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?

Discloses core behavior: screening against OFAC list, mixer exposure, wallet age, output categories (PASS/WARN/BLOCK), signed receipt, and pricing. No annotations, so description handles transparency well.

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 front-loading purpose, then additional detail and pricing. Minimal redundancy.

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

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

No output schema, but description mentions return values (PASS/WARN/BLOCK and signed receipt). Sufficient for selection but could detail receipt 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?

Schema covers both parameters (wallet, chains) with descriptions. The description restates schema info without adding new meaning, so baseline 3.

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

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

Clearly states it screens wallets for sanctions/AML/KYT against OFAC SDN list, with mixer exposure and wallet age, returning a signed receipt. Distinguishes from siblings by specifying multi-chain support and cryptographic attestation.

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 compliance screening but no explicit comparison to sibling tools like sanctions_screen or crypto_wallet_forensics. Lacks when-to-use or when-not-to-use guidance.

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

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

No annotations are provided, so the description carries the full burden. It discloses resilience ('returns whatever venues respond') and pricing ($0.05 per call with x402 payment) but omits details on rate limits, authentication steps, or error handling for invalid symbols.

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 somewhat repetitive, restating the same data outputs twice. While it front-loads the key information, there is redundancy that could be removed to improve conciseness.

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

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

With no output schema, the description should briefly indicate the return format, but it does not. It also lacks details on data freshness or cost implications upfront. Despite mentioning resilience and pricing, critical usage context 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?

Schema coverage is 100% and the description reiterates the parameter as 'coin ticker' with examples. This adds no new meaning beyond the schema, so the baseline score of 3 is appropriate.

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

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

The description clearly states the tool returns perpetual funding rates, open interest, long/short ratios across specific exchanges, plus computed arbitrage spread and crowding signal. It specifies input as a coin ticker, making the purpose highly specific and actionable.

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 targets 'trading and funding-arbitrage agents' but does not provide when-not-to-use scenarios or alternatives among sibling tools. The context is adequate but lacks exclusionary 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, the description carries full burden. It discloses data sources, fee adjustment, profitability flagging, and pricing ($0.05 per call). However, it does not mention rate limits, error handling (e.g., missing ticker), or output format, leaving gaps for an agent to understand failure modes.

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 has two sentences that partially repeat content (e.g., 'DEX vs CEX arbitrage spread: the price difference...'). It is somewhat verbose and could be consolidated into a single clear sentence without losing meaning.

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

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

No output schema is provided, so the description must explain return values. It only says 'flags any profitable arbitrage opportunity' without specifying the format (number, boolean, text). This leaves ambiguity for an agent expecting structured output.

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

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

Schema description coverage is 100% with a single parameter 'symbol' described as 'Coin ticker, e.g., 'ETH', 'WBTC', 'ARB''. The description adds no new details beyond confirming it expects a coin ticker. Baseline 3 is appropriate as schema already documents the parameter.

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

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

The description clearly states the tool computes the fee-adjusted net spread between DEX (DexScreener) and CEX (Binance/Bybit) and flags profitable arbitrage opportunities. It distinguishes itself from sibling tools by specifying 'For arbitrage agents' and explicitly contrasting with raw price comparison.

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

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

The description states 'For arbitrage agents' but does not explicitly mention when not to use this tool or name alternatives. It implies the context (arbitrage detection) but lacks exclusions or comparisons with related sibling tools like crypto_signal_fusion or crypto_pre_trade_verdict.

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

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

With no annotations, the description adds useful behavioral traits: EVM safety check for EVM chains vs Solana-only pair listing, pricing and payment method (x402), and the bundled safety check. However, it omits details on the safety check's reliability or recency of 'newly launched'.

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 verbose and repetitive, with almost identical content in two paragraphs. Extraneous details like pricing could be omitted. It could be tightened without losing meaning.

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

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

No output schema exists, but the description lists key return fields (pool, base token, price, liquidity, age) and mentions the safety check. For a list tool with 3 params, this is fairly complete, though the safety check output is unspecified.

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

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

Schema coverage is 100% with descriptions for each parameter. The description reinforces 'chain + limit' input but adds no new semantics beyond rephrasing. Baseline 3 is appropriate.

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

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

The description clearly states the tool lists newly launched DEX pairs/pools per chain with a bundled safety check, specifying the source (GeckoTerminal) and output fields (pool, base token, price, liquidity, age). It is specific and distinct from sibling tools.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention exclusions, prerequisites, or context for optimal usage, leaving users to infer appropriateness.

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 it returns a verdict with a signed, offline-verifiable receipt, costs $0.05 per call via x402/USDC, and fuses three analyses. It does not elaborate on error handling or rate limits, but the core behavior is 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 somewhat repetitive: the first and last paragraphs essentially restate the same information. It could be more concise by removing duplication while preserving the key details about pricing and receipt.

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 fusing three separate functions and no output schema, the description adequately explains the tool's purpose, supported chains, input parameters, and pricing. It mentions a signed receipt but doesn't detail the verdict format, which is a minor gap. Overall, it is complete enough for an AI agent to decide when and how to invoke 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?

Schema has 3 parameters with 100% description coverage. The description adds meaning beyond the schema: clarifies that chain defaults to 'base', token can be EVM contract or SPL mint, and wallet is optional for counterparty screening. It also summarizes inputs as 'token (+chain, optional wallet)'.

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

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

The description clearly states it provides a GO/CAUTION/NO-GO pre-trade verdict fusing token safety, wallet screening, and market signal. It directly answers 'Should I buy this token now?' and distinguishes from sibling tools like crypto_token_safety, compliance_wallet_screen, and crypto_signal_fusion by positioning itself as a replacement for three separate calls.

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 'Should I buy this token now?' and explains it replaces three separate calls, giving clear context for when to use it. It also states supported chains (EVM + Solana) and pricing. However, it does not explicitly specify when NOT to use it, though the purpose is well-defined.

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

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

No annotations provided. Description discloses data freshness, fusion sources, and cost ($0.02/call with x402 payment). However, it lacks details on failure modes, latency, or required permissions. Some behavioral context is present.

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 competitor note and pricing. It is relatively concise but could be more structured. No wasted words, but the information is dense.

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 2 params and no output schema, the description covers purpose, data sources, freshness, availability, and pricing. It lacks return structure (e.g., confidence score format) but is largely complete.

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

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

Schema coverage is 100%, but description adds value by explaining timeframe options (5m,15m,1h,4h) with default 1h, and symbol as coin ticker. This goes beyond the schema's minimal descriptions.

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

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

The description clearly states it provides a fused trading signal (long/short/neutral) with confidence, combining multiple data sources. It uses specific verbs 'fusion' and 'signal' and distinguishes itself from competitors selling separate components.

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

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

It gives context for usage ('Should I go long or short?', 'Derivatives trading signal for any altcoin') but does not explicitly mention when not to use or contrast with sibling tools like crypto_derivatives_radar or crypto_pre_trade_verdict.

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 convey behavioral traits. It discloses pricing ($0.10 per call, x402 payment on USDC Base mainnet), the input parameters and their formats, and the output contents (safety score, holders, etc.). It does not mention rate limits or side effects, but for a read-only dossier tool this is acceptable.

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 verbose and repetitive, e.g., 'Full degen token dossier in one call' followed by a list that is then partially repeated. The first sentence contains core information, but redundancy reduces clarity. It could be streamlined without losing content.

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

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

Given the tool has only 2 parameters and no output schema, the description provides sufficient context: use case (due diligence before buying), supported chains, pricing/payment, and the fields returned. While it lacks authentication details beyond payment, it is largely complete for a tool of this complexity.

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

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

Schema description coverage is 100%, with both 'chain' and 'token' parameters already well-described in the schema. The tool description reiterates the parameter names and types but adds no new semantic detail beyond what the schema provides. Thus it meets the baseline 3 but does not exceed it.

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

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

The description explicitly states it's a 'full degen token dossier' and lists key components: safety score, honeypot/tax, top holders, concentration, liquidity/FDV/volume/pool-age, contract control, AI red-flag narrative. It distinguishes itself from a 'plain safety check' and mentions it's a premium tier. The verb 'dossier' combined with the detailed list clearly defines 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 indicates usage 'before aping' and positions itself as a premium tier above a plain safety check, implying deeper due-diligence. It also specifies supported chains (EVM and Solana) and pricing. However, it does not explicitly name sibling tools like 'crypto_token_safety' or provide when-not-to-use guidance, lacking full comparative 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 provided, the description carries the full burden. It explains the bundled checks, the scoring mechanism, and the payment method (x402, $0.05). It does not mention authorization, rate limits, or side effects, but as a read-only check this is less critical.

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 contains useful information but is somewhat repetitive (e.g., 'Token safety check before buying' appears twice). It is well-structured but could be tightened without loss of meaning.

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

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

Despite lacking an output schema, the description sufficiently explains the output (0-100 score with verdict) and covers input, usage context, pricing, and payment. It provides a complete picture for an agent 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 100% with descriptions for both parameters. The description adds value by stating 'Input: token contract address + chain', providing an example address, and listing supported chains. This goes beyond the schema's enum 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's function: 'Token safety check before buying — is this token a honeypot or a rug pull?' It lists specific checks (honeypot, taxes, holder concentration, LP lock, liquidity) and the output (0-100 risk score with verdict). This distinguishes it from siblings like solana_token_safety which targets a different chain.

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 targets 'trading agents screening a token' and notes that one call replaces three lookups, indicating efficiency. It provides context (EVM chains) and pricing, but does not explicitly state when not to use or compare to alternatives like crypto_token_dossier.

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

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

No annotations are provided, so the description carries the burden. It discloses the output (nodes+edges, ranked counterparties, patterns, signed receipt), payment ($0.15/x402 on Base), and scope (EVM, ERC-20). However, it lacks details on rate limits, authentication, or whether the tool mutates state (likely read-only).

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

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

The description is somewhat redundant, repeating 'Multi-hop wallet forensics' and the list of outputs. It is adequately structured but could be more concise 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?

With no output schema, the description explains return values in detail: flow graph, ranked counterparties, patterns, and signed receipt. It also covers supported chains and pricing. This is sufficient for a tool with three parameters, though an example would strengthen completeness.

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

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

Schema description coverage is 100%, with parameters already documented. The description repeats the parameter meanings (depth 1-3, chain default base, wallet format) but adds no significant extra meaning beyond the schema, warranting baseline 3.

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

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

The description clearly states the tool's function: multi-hop wallet forensics for ERC-20 counterparty graph, ranked counterparties, pattern detection, and signed receipt. It specifies EVM chains and payment, and the name is descriptive. It distinguishes from siblings like crypto_wallet_xray by focusing on flow graphs and patterns.

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 tracing fund movements and detecting patterns but does not explicitly state when to use this tool over alternatives, nor does it provide exclusions or prerequisites.

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

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

No annotations exist; the description carries full burden. It discloses data sources (Blockscout, DexScreener, OFAC list), supported chains, payment requirement, and bundled nature. Missing details on caching, rate limits, or error handling, but overall informative.

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 somewhat repetitive (e.g., same information stated twice) and includes a grammatically awkward sentence ('where primitives serve one field per call this returns...'). It could be more concise 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 no output schema and few parameters, the description covers inputs, output content, payment, and supported chains. It lacks output format or error behavior, but provides sufficient context for most 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 100%, so both parameters are already well-documented in the schema. The description merely restates 'Input: wallet address + chain' without adding new semantic context, meeting the baseline.

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

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

The description clearly states the tool performs wallet risk analysis, returning native + ERC-20 balances, USD portfolio valuation, token count, and an OFAC sanctions flag. It distinguishes itself from 'primitives' that serve one field per call, making the purpose explicit and differentiated.

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 identifies target users ('on-chain analysis, compliance and trading agents') and mentions cost ($0.05 per call via x402). However, it does not explicitly state when to use this tool versus specific siblings or when not to use it, 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?

No annotations provided, so description carries full burden. It discloses that it queries the official NVD database, returns description, CVSS, CWE, references, and mentions worldwide access and price. Lacks details on error handling or rate limits, but adequate for a lookup 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 somewhat repetitive, with the first two paragraphs duplicating the same information. Could be more concise by removing 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?

The description lists return fields (description, CVSS, CWE, references, status) but does not explain structure or handle potential conflicts between cve_id and keyword parameters. Absence of output schema suggests need for more 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 describes all three parameters (limit, cve_id, keyword) with examples. The description adds examples and clarifies input format, but does not add significant meaning beyond schema (100% 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 it is a security vulnerability lookup against the official NVD database, specifying exact CVE ID or keyword/product search. It differentiates from siblings (which are diverse) by its focus on CVEs.

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 targets devsecops, SBOM, and dependency-audit agents, and mentions the pricing model. However, it does not explicitly contrast with alternatives or state when not to use it.

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

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

No annotations are provided, so the description carries full burden. It discloses geographic coverage (US), pricing ($0.05 per call with x402 payment), and the specific sections returned. It does not mention failure modes or rate limits, but overall provides good behavioral context.

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

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

The description is informative but contains redundancy (e.g., repeating the source). It is front-loaded with the key purpose and then adds details. Minor redundancy prevents a perfect score.

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

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

Given no output schema, the description fully explains return values (key label sections: drug interactions, warnings, contraindications, indications, boxed warning) and notes coverage and pricing. Complete for a simple lookup tool.

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

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

Schema coverage is 100% with clear descriptions for both parameters. The tool description adds little beyond the schema, merely restating that lookup is by generic or brand name. Baseline 3 is appropriate as schema does the heavy lifting.

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

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

The description clearly identifies the tool as a lookup for drug interactions, warnings, and contraindications from official FDA labels, specifying the verb (lookup), resource (FDA drug labels), and scope (by generic or brand name). This effectively differentiates it from unrelated sibling tools.

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

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

The description states it is for healthcare, pharmacy, and clinical-decision-support agents and explicitly notes it is not medical advice. However, it does not explicitly discuss when not to use or mention alternative tools, though siblings are unrelated.

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 data freshness (published ~16:00 CET on working days), pricing ($0.01 per call via x402/USDC on Base), and that rates are reference not live. It could further mention rate limits or idempotency, but current info is sufficient for safe use.

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 contains redundant sentences (e.g., 'Reference rates (published ~16:00 CET on working days), not live market rates.' appears twice). Could be more concise by removing repetition and front-loading essential info.

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

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

Given no output schema, description explains it returns the EUR reference rate with real observation date, which is adequate for a simple lookup tool. Could specify response fields (e.g., rate value, currency, date) for completeness, but current info is sufficient for basic usage.

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

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

Schema coverage is 100%, so baseline is 3. Description reiterates schema descriptions (3-letter ISO code, ISO date format, frequency options) without adding new information beyond what the schema already provides.

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 retrieving official ECB euro reference exchange rates, specifying 29 currencies, latest or by date, and distinguishes it from live market rates. It uses specific verb 'lookup' and resource 'ECB euro reference exchange rates', making purpose 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 provides context for use cases: pricing, accounting, FX, treasury agents. It states 'not live market rates', implying when not to use. However, it does not explicitly exclude alternative tools among siblings (e.g., crypto exchange rate tools) or provide a direct when-not-to-use statement.

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

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

No annotations are provided, so the description must carry the full burden. It discloses the cost per call ($0.01 via x402 payment), multilingual support, and source (CELLAR). However, it does not mention rate limits, idempotency, or any side effects. For a read-only search, the cost and return format are useful but not exhaustive.

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

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

The description contains some redundancy, notably repeating the multilingual support and legal research context. It is not overly long but could be tightened by removing duplicate phrases. The structure is adequate but not exemplary.

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 (3 parameters, no output schema), the description covers essential aspects: purpose, inputs, return fields, cost, and language options. It lacks explanation of pagination or behavior on empty results, but for a straightforward search tool, it is mostly complete.

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

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

Schema description coverage is 100% (all three parameters have descriptions). The description adds context that the search is full-text title search and reinforces the language list. However, it does not provide significant additional meaning beyond what the schema already conveys, so the baseline of 3 is maintained.

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 identifies the resource (EUR-Lex) and action (search by keyword), specifies supported content types (EU legislation, treaties, case law, legal acts) and return fields (CELEX number, title, date). While it distinguishes from other legal tools by naming the official EU database, it does not explicitly contrast with siblings like fr_legifrance_search, so a score of 4 is appropriate.

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

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

The description states the tool is 'for legal-research, regulatory and compliance agents', providing general usage context. However, it offers no when-not-to-use guidance or explicit alternatives among siblings. The usage inference is mostly implicit from the resource name.

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 does well: it discloses the output fields, pricing model ($0.01 per call, USDC on Base), and input parameters. It does not discuss rate limits or error behavior, but is transparent about the data returned.

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 repetitive: 'EV charging stations worldwide from Open Charge Map' appears twice, and the list of returned fields is duplicated. It could be more concise 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?

For a tool with 4 parameters, no output schema, and no annotations, the description covers the return fields adequately but lacks details on output structure, pagination, and error conditions. It is reasonably complete but has 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 100%, so baseline is 3. The description adds only that the distance is in 'km' and max results is 'max stations', which is already in the schema. No significant new meaning is added beyond what the schema provides.

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 function: to return nearby EV charging stations given a location and radius, with specific fields like operator, connector type, power, points, and status. It mentions the data source (Open Charge Map) and worldwide coverage, making the purpose 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 says 'For routing, fleet and trip-planning agents', which gives a high-level context but does not explicitly state when not to use the tool or compare it to alternatives. Since no sibling tools perform a similar function, the guidance is adequate but minimal.

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 cost ($0.01 per call) and data source (adsb.fi), but does not mention rate limits, authentication, or bounding box size limits. Payment info adds value, but missing constraints lower the score.

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 verbose and repetitive, with nearly identical sentences appearing twice. It could be more concise by removing redundancy. The structure is otherwise clear but not optimal.

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 is simple, but there is no output schema. The description lists fields (position, altitude, etc.) but does not specify the response structure (e.g., array). For a data retrieval tool, more detail on return format would be helpful.

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

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

Schema coverage is 100%, so parameters are fully described in the schema. The description repeats the bounding box concept but adds no new semantics beyond what the schema provides. Baseline 3 is appropriate.

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

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

The description clearly states it returns real-time aircraft states within a bounding box using a specific verb ('get every aircraft') and resource ('aircraft states'). It is distinct from the sibling tools, which are unrelated to flight tracking.

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 it is for 'travel, logistics, airspace-monitoring and tracking agents,' providing context. However, it does not explicitly state when to use versus alternatives or when not to use. Since no sibling tool is similar, this is acceptable but not perfect.

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 pricing model ($0.05 per call, x402 payment) and outlines return fields (title, identifier, nature, date, legal status). It implies a read-only operation without stating it explicitly, which is acceptable for a search/lookup 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 verbose and repeats information (e.g., mentions 'Official Légifrance' and 'French law' multiple times). It includes pricing which is useful but could be more concise. The structure is not fully front-loaded; key information like 'keyword search' and 'text lookup' appears later.

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

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

Given no output schema, the description explains return fields and distinguishes between search and lookup modes. It covers corpus options and default. However, it lacks examples or edge cases (e.g., handling of missing IDs or invalid corpuses).

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 100% description coverage, so the description adds little beyond what the schema already provides. It restates the two usage modes (keyword + corpus or text_id) but does not enrich the meaning of individual parameters beyond the schema descriptions.

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

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

The description clearly states the tool searches and looks up French legal texts on Légifrance, specifying verbs 'search' and 'lookup' and the resource 'French legal texts, codes and articles'. It distinguishes from sibling eurlex_search by explicitly complementing EUR-Lex on the national French side.

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: it is for French law search/lookup, complements EUR-Lex, and is intended for 'legal-research, regulatory and compliance agents'. It does not explicitly state when not to use it, but the mention of EUR-Lex as the EU counterpart gives implicit 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?

No annotations are present, so the description bears full responsibility. It describes the tool as a 'lookup' and 'verification', implying a read-only, non-destructive operation, which is adequate. However, it lacks details on rate limits, authentication, or potential errors.

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 repetitive, essentially stating the same information in two paragraphs. It could be condensed into a single, well-structured sentence without loss of clarity.

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

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

Despite the lack of an output schema, the description enumerates the returned fields (legal name, administrative status, NAF/APE code, etc.) and includes pricing. It covers the essential information for an agent to invoke the tool correctly.

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

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

Schema description coverage is 100%, and the description adds minimal value beyond the schema, such as noting that SIRET, SIREN, or company name can be used. The schema already provides detailed parameter descriptions.

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

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

The description clearly states it is a French company/establishment lookup by SIREN, SIRET, or name against the official INSEE Sirene register. It specifies the returned fields (legal name, administrative status, NAF/APE code, etc.), making the purpose distinct from sibling tools like uk_companies_search.

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 targets KYB, AML, and supplier due-diligence agents in France, providing clear usage context. However, it does not mention when not to use the tool or suggest alternatives.

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

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

With no annotations, the description carries full behavioral burden. It states it's a real-time worldwide lookup, notes pricing ($0.01 via x402 payment), and indicates read-only nature. Missing rate limits, authentication requirements, and error handling, but adequately describes core behavior.

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

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

The description is relatively concise and front-loaded with the primary action and return data. It includes useful extras like pricing and use cases without excessive verbosity, though the contradictory input statement adds unnecessary confusion.

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 with full schema coverage and no output schema, the description should be self-sufficient. It covers purpose and usage but fails on input accuracy (contradiction) and does not address error cases (e.g., invalid LEI). This limits agent 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?

The description claims 'LEI code or legal name' as input, but the schema requires a strict 20-character LEI pattern. This contradicts the schema and misleads the agent about valid inputs. Additionally, schema coverage is 100%, so no param info beyond schema is needed, but the misleading statement severely harms usefulness.

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: looking up Legal Entity Identifiers via the GLEIF registry, listing return fields (legal name, status, jurisdiction, etc.) and use cases (regulatory reporting, KYB). It does not explicitly differentiate from sibling tools, but the specificity is sufficient for a distinct 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 context for when to use (regulatory reporting, counterparty agents) and input format ('LEI code or legal name'). However, it does not specify when not to use or offer alternatives, leaving the agent without exclusion 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, the description fully covers behavioral traits: deterministic algorithm, local execution, pricing ($0.01 per call, USDC on Base mainnet), and return structure (valid/invalid with reason, country code, etc.). No contradictions or 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 somewhat repetitive (e.g., 'IBAN format validation' and 'SEPA/EU structural validation' restated). While front-loaded with key info, it could be more concise by removing redundant phrasing.

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 required parameter, no output schema, and moderate complexity, the description is comprehensive: it covers purpose, algorithm, limitations, pricing, and output format. An AI agent can fully understand tool behavior and invocation.

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

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

Schema coverage is 100% (one parameter with example). The description adds meaning by explaining the validation algorithm, structural extraction, and non-existence check. This goes beyond the schema's example, justifying a score above baseline 3.

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

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

The description clearly states the tool validates IBAN format using ISO 13616 mod-97, extracts structural components, and explicitly distinguishes from account existence checks. It provides a specific verb ('validate'), resource ('IBAN'), and scope ('SEPA/EU coverage'). No ambiguity.

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 'Format check only — does NOT verify the account exists' and 'For payment, onboarding and treasury agents', giving clear context on when to use. It does not explicitly list alternative tools or when not to use, but the scope is well-defined.

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

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

No annotations provided, so the description carries full burden. It details what the tool returns (value, as_of date, next_release cadence, receipt) and mentions pricing and payment method. This gives sufficient transparency for a read-only 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 detailed (5 sentences) but efficient, front-loading the core purpose. Every sentence adds value; could be slightly shorter but no unnecessary 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 only 2 parameters with full schema coverage and no output schema, the description thoroughly explains the output structure (value, as_of, next_release, receipt). No gaps in understanding what the tool returns.

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

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

Schema description coverage is 100%, but the description adds context: area default 'U2' and lists exact indicator names (e.g., 'deposit_facility_rate'). This goes beyond the schema's generic descriptions.

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

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

The description clearly states it's a 'Macro economic snapshot API' for Eurozone indicators, listing specific data points (HICP, ECB rates, unemployment, EUR FX) and source (ECB). It differentiates from siblings like ecb_exchange_rate by covering a broader set of indicators.

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

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

The description targets 'trading/research agents' and mentions context needed before trading, but does not explicitly state when to use versus alternatives (e.g., ecb_exchange_rate for just FX). No exclusions or when-not-to-use guidance.

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

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

With no annotations provided, the description must fully disclose behavior. It explains the tool generates a report (non-destructive read), mentions the cost ($0.10 per call, x402 payment), and describes the data sources. It does not discuss rate limits or error scenarios, but the read-only nature and payment requirement are adequately covered.

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 front-loads the purpose but repeats nearly identical phrases twice, making it longer than necessary. It includes pricing and input summary, but the redundancy harms conciseness. It's adequate but could be more streamlined.

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 tool (multiple data sources, no output schema), the description provides a reasonable overview of the report contents (headline, outlook, signals, risks). However, it lacks details on response format and does not fully compensate for the absence of an output schema, leaving some ambiguity for agents.

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

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

Schema description coverage is 100%, so the schema already fully documents both parameters (depth and focus) with defaults. The description adds no new parameter information beyond a brief summary, thus meeting the baseline but not exceeding it.

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

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

The description clearly identifies the tool as an AI market intelligence report combining cross-exchange perp derivatives, fused directional signals, and euro-area macro data into a synthesized output. It distinguishes from sibling tools such as crypto_derivatives_radar or macro_snapshot by offering a unified, multi-source report in a single call.

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

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

The description states the tool is 'for research and trading agents' and specifies inputs (focus and depth), providing clear context for when to use it. However, it lacks explicit guidance on when not to use it or direct comparisons to alternative tools, though the combined nature implies it's for holistic analysis.

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 format (GeoJSON, area, levels, height, name), pricing ($0.01 per call, USDC on Base), and global coverage. It lacks mention of potential rate limits or data completeness but is otherwise 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 appropriately front-loaded with the core purpose. However, there is minor redundancy (two nearly identical phrases about building footprint via Overpass). Still clear and 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?

For a tool with 4 params and no output schema, the description covers purpose, input, output, pricing, and use cases. Missing details like coordinate system (WGS84) and potential data gaps, but still fairly complete.

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

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

Schema coverage is 100% (baseline 3). The description adds context: lat/lon and bbox as alternatives, radius range (1-200m, default 50), and bbox max span (~2km). This goes beyond the schema descriptions.

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

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

The description clearly states the tool retrieves OpenStreetMap building footprints via Overpass, specifying the output as GeoJSON geometry, footprint area, levels, and height. It distinguishes itself from sibling tools (crypto, legal, etc.) as the only geospatial building footprint tool.

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 target use cases (real-estate, insurance, solar, geospatial, urban-planning agents) and input methods (lat/lon+radius or bbox). While it does not explicitly list when not to use or alternatives, the sibling tools are diverse enough 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 carries full burden. It discloses pricing ($0.05/call), coverage (100+ offices), and input behavior (publication number triggers biblio lookup, other fields trigger search). However, it does not explicitly state that it is a read-only operation or discuss error handling, rate limits, or failure modes.

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 first sentence, but it contains significant redundancy (the two main paragraphs repeat similar content). It could be more concise by merging or removing duplication while retaining all 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?

Given the complexity (7 parameters, no output schema), the description provides a comprehensive overview of return fields (publication number, country, kind code, dates, titles, applicants, inventors, classifications, family id), input options, pricing, and coverage. It lacks details on pagination or error responses but is largely complete.

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

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

Schema coverage is 100%, yet the description adds significant value by explaining CQL prefix syntax (e.g., 'ti=', 'in=', 'pa=') and clarifying that setting publication_number switches to biblio lookup mode. This enhances understanding beyond the schema descriptions alone.

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

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

The description clearly states the tool's purpose: European patent search and bibliographic lookup via the EPO OPS, specifying what it returns (publication number, country, dates, etc.) and the supported input methods (number or CQL search). It distinguishes itself from sibling tools by its unique domain (patents), with no overlapping functionalities.

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 mentions use cases (IP due-diligence, freedom-to-operate, prior-art, R&D) and provides context such as coverage and pricing. However, it lacks explicit exclusions or comparisons to sibling tools, though they are mostly unrelated.

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

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

With no annotations provided, the description carries the full burden. It discloses the cost ($0.05 per call via x402 payment on Base mainnet) and the data returned (probabilities, volume, liquidity, resolution status). It does not mention rate limits, failure modes, or authorization details beyond payment, but the behavioral traits are largely transparent for a read-only 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 moderately concise with three sentences, but the first two sentences are largely redundant, both stating the tool provides live odds and probabilities. This repetition wastes space and could be merged or removed for better conciseness.

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

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

Given the simple input (one string parameter) and no output schema, the description adequately explains the return structure (outcomes with probability, volume, liquidity, resolution status) and the cost. It lacks details on error handling or edge cases, but for a straightforward data retrieval tool, it covers the essential context fairly well.

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

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

Schema description coverage is 100% for the single parameter 'market', so the baseline is 3. The description adds value by providing concrete examples ('2654605' or 'will-it-rain-tomorrow') but does not elaborate on formatting or behavior beyond what the schema already states.

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 live prediction market odds and implied probabilities from Polymarket, specifying the input (market id or slug) and output (outcome probabilities, volume, liquidity, resolution status). It distinctly states the action and resource, differentiating it from sibling tools like polymarket_resolution which likely handles market resolution.

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

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

The description mentions the tool is 'for event-forecasting, hedging and research agents,' which gives a general usage context but does not provide explicit when-to-use or when-not-to-use guidance compared to sibling tools like polymarket_resolution. It lacks exclusions or alternatives, so usage is implied but not well-defined.

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

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

No annotations provided, so description carries full burden. It discloses that the winning outcome is 'derived from final outcome prices, only when unambiguous — never invented,' and mentions resolution source, end date, condition id/slug. Also includes pricing and payment method, providing full behavioral context.

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

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

Description is informative but somewhat verbose. However, key information is front-loaded and structured logically. Every sentence adds value, though some repetition (e.g., mentioning 'Polymarket resolution oracle via Gamma API' twice) could be trimmed.

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

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

Given no output schema, description adequately explains return fields (closure status, winning outcome, resolution source, end date, condition id/slug). It covers inputs, pricing, and distinct use case. Could add details about error handling or response format, but sufficient for an agent.

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

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

Input schema has 100% description coverage, so baseline is 3. Description merely restates 'Input: market slug or condition id' without adding syntax, defaults, or usage examples beyond the schema. No additional semantic value.

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

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

The description clearly states the tool returns Polymarket resolution status via Gamma API, including winning outcome and resolution source. It explicitly distinguishes from live odds, a sibling tool (polymarket_odds), by noting it returns whether a market is closed and which outcome won.

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

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

The description states the tool is 'distinct from live odds' and suitable for 'settlement, audit, research and event-forecasting agents,' implying when to use. It does not explicitly state when not to use, but the contrast with live odds provides context. It also specifies inputs (slug or condition id).

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

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

No annotations are provided, so the description carries the full burden. It discloses that the proof is Ed25519-signed, timestamped, offline-verifiable, and that the issuer never sees the content if only a hash is sent. It also states the cost and payment method, providing comprehensive behavioral 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 somewhat verbose and repeats key information (e.g., 'Notarize a SHA-256 hash...' appears twice). While it is well-structured with clear sections, it could be more concise without losing content.

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

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

There is no output schema, but the description sufficiently explains the return format (a timestamped, Ed25519-signed proof-of-existence receipt verifiable offline). Given the tool's simplicity and the richness of sibling tools, the description provides adequate context for an AI agent 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?

Schema description coverage is 100% with clear descriptions for each parameter. The description adds value by explaining the relationship between 'hash' and 'content' (alternative inputs), the purpose of 'memo', and content size limits, which goes beyond the schema.

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

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

The description clearly states the tool notarizes a document or data hash by submitting a SHA-256 hash and returning a timestamped, Ed25519-signed proof-of-existence receipt. It explicitly distinguishes itself from blockchain-anchored or legal timestamps, making the purpose 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 provides explicit guidance on when to use the tool (to prove existence at a point in time) and what it is not (not a legal or blockchain timestamp). It also mentions the pricing model and payment method, giving clear context for usage.

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 data source (FDA openFDA), geographic coverage (US), pricing ($0.01 per call via x402 payment), and return fields (recall number, classification, etc.). No annotations exist, so description carries full burden; it covers key behavioral aspects 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?

The description contains redundancy (first sentence repeats later content). While informative, it could be more concise without losing clarity.

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

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

No output schema exists, but description lists return fields. Parameter descriptions are complete. The tool's purpose and inputs are well-covered, making it adequate for agent invocation.

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

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

Schema coverage is 100% with descriptions. The description adds contextual meaning by explaining how to search (by product, firm, reason) and filter by class. This enhances understanding beyond schema alone.

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

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

Description explicitly states it is for product recall lookup of drugs/devices/food using FDA openFDA data, with clear differentiation from sibling tools which are unrelated (e.g., crypto, legal, compliance).

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?

Mentions specific use cases (e-commerce, supply-chain, pharmacovigilance, compliance) but does not explicitly state when not to use or compare to alternatives. Given no similar sibling, the guidance 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?

Discloses pricing ($0.05/call with x402 payment on Base mainnet), fuzzy matching behavior, non-binary output, and returned context fields. No annotations provided, so description carries full burden; it adequately covers behavioral traits 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?

Description is concise yet comprehensive, front-loading key information. Every sentence adds value: purpose, pricing, behavior, use cases, input hint. 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 the tool's complexity (fuzzy matching, multiple params, no output schema), the description fully covers return format (matches with similarity, EU reference, type, programme, designation details), use cases, and input. No gaps identified.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds minimal extra value beyond schema (example input, mention of 'human review'), but does not significantly enhance parameter understanding.

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

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

Clearly states the tool screens against the EU consolidated sanctions list and returns ranked matches with similarity scores and context. Differentiates from siblings by specifying the exact official list and its usage for KYB/AML/compliance.

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

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

Provides explicit use cases ('For KYB, AML and payment-compliance agents') and clarifies non-binary output requiring human review. Implicitly suggests not for binary yes/no needs, but does not explicitly name 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?

Despite no annotations, the description discloses that the tool fuses four scored modules (token security, liquidity depth with slippage estimates, deployer history, holder concentration) and specifies cost ($0.05 per call via x402 payment on Base mainnet). This provides good behavioral clarity beyond a simple read operation.

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 front-loaded with key decision types and modules, then ends with cost info. It is informative but slightly verbose; could tighten without losing content. 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?

No output schema is provided, and the description does not detail the return format or structure (e.g., whether it returns a JSON with scores or just a verdict). For a tool outputting scored modules, this omission leaves the agent with insufficient context to parse the response. Cost and module info are good, but return format is critical.

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 'mint' has a schema description that matches the tool's purpose. The description does not add additional semantics beyond the schema, which already defines it as an SPL token mint address. Schema coverage is 100%, so baseline is appropriate.

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

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

Description clearly identifies this as an all-in-one Solana pre-trade decision tool producing BUY-SAFE/CAUTION/AVOID verdicts. It specifies the resource (Solana token) and action (evaluate and decide). Distinct from siblings by consolidating four modules into one call.

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

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

Description implies usage as a replacement for 3-4 separate lookups and is 'built for a trading/sniping agent's risk-review pipeline.' However, it lacks explicit guidance on when not to use it vs. alternatives like solana_token_safety. Usage context is clear but not exclusive.

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 the checks: static (mint/freeze authority, holder concentration) and behavioral (liquidity, churn, recent dump, tx velocity). It also mentions the false-positive guard and price. Shows transparency about methodology but does not describe output format beyond verdict and score.

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

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

The description is moderately concise: three sentences, front-loaded with purpose. However, it includes extra details (price, blue-chip guard) that could be streamlined. Each sentence adds value, but overall length could be reduced without losing clarity.

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

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

Given no output schema, the description covers return values (verdict and score). It explains the analysis scope (static + behavioral) and special features. Missing detail on output structure (e.g., additional fields) is a minor gap, but overall complete for a safety analysis tool.

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

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

Schema coverage is 100% (context signals). The schema already defines 'mint' as base58 address and 'deep' as boolean. Description adds minimal extra meaning (e.g., example address), but mainly restates purpose. Parameters are adequately documented in schema, so no significant value added.

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: Solana SPL token safety analysis, rug pull/honeypot/scam detection. It specifies the verdict (SAFE/RISKY/CRITICAL) and a 0-100 score. It differentiates from siblings like 'crypto_token_safety' by targeting Solana tokens and combining static and behavioral checks.

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 indicates usage 'before trading' and highlights features like blue-chip false-positive guard and catching behavioral rugs. It implies when to use (pre-trade) but does not explicitly contrast with sibling tools or state when not to use. Context is clear but lacks direct alternatives.

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

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

With no annotations, the description carries the full burden. It discloses the return fields, pricing ($0.05 per call with x402 payment), and coverage limitations. It does not detail error handling, rate limits, or behavior when no building is found, but the provided info is substantial.

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 repetitive: the first four sentences are essentially duplicated in a later block. It could be condensed into a single coherent paragraph without losing information, indicating poor conciseness.

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

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

Given the complexity (3 parameters, no output schema, no annotations), the description covers return fields, use cases, pricing, and coverage. However, it lacks details on output format, error states, and edge cases, leaving some gaps for an agent.

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

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

Schema coverage is 100%, so the schema already documents the three parameters (lat, lon, quality). The description only mentions 'Input: lat/lon (+imagery quality)' without adding meaning beyond the schema descriptions. Baseline 3 is appropriate.

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

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

The description clearly states the tool returns rooftop solar potential metrics (max panel count, usable roof area, annual sunshine hours, carbon-offset factor) for a given coordinate, sourced from the official Google Maps Platform Solar API. This specific verb+resource combination distinguishes it from sibling tools like climate_risk_score or osm_building_footprint.

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: 'sizing solar installs, real-estate energy scoring, or carbon/ROI estimates.' It also notes worldwide partial coverage with EU well covered, implying limitations. However, it does not offer exclusions or comparisons to alternative tools for similar tasks.

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 reveals pricing ($0.05 per call), data source (official TED), and return fields (publication number, title, buyer, etc.), indicating a read-only search. No destructive or auth details needed for this type of 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, front-loads the tool's purpose, and includes essential details (pricing, filters, output fields) in a single paragraph. Minor room for improvement by using bullet points for clarity.

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

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

Despite no output schema, the description enumerates the return fields, lists all parameters (covered in schema), provides pricing, and specifies use cases. This is fully adequate for a search tool with clear inputs and outputs.

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

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

Schema coverage is 100% with clear parameter descriptions. The description adds general context (filters by keywords, country, CPV) but does not provide additional semantics beyond what the schema already conveys. Baseline 3 is appropriate.

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

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

The description clearly states the tool searches EU TED for public procurement notices, specifies the geographic scope, and mentions key filters. It distinguishes this tool from its numerous siblings by focusing on a specific domain (EU public procurement) with no overlap evident.

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 this is for business-development, bid, and market-intelligence agents, giving clear use context. However, it does not provide when-not-to-use guidance or mention alternatives among the sibling tools.

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

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

No annotations are provided, so the description carries full burden. It discloses pricing ($0.01 per call), payment method (USDC on Base mainnet), data source (official register), and return fields (status, type, incorporation date, etc.). It is a read-only operation, which is implied but not explicitly stated as non-destructive.

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

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

The description is long but well-structured: it starts with the core purpose, then details capabilities, pricing, and target users. Each sentence adds information, though some repetition (e.g., 'Official UK register coverage' appears twice) slightly reduces conciseness.

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

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

Despite having no output schema, the description thoroughly lists return fields (status, type, incorporation date, registered office address, SIC codes, insolvency history, officers with ECCTA identity verification). It also covers pricing, use case, and input examples, making it self-sufficient for an agent to understand the tool's behavior and output.

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

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

Schema description coverage is 100%, but the description adds value by providing concrete examples ('Tesco', '00445790') and explaining the distinct role of company_number for detailed profiles. This goes beyond the schema's terse descriptions.

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

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

The description clearly states the tool searches the official UK Companies House register with two distinct operations: search by name/number or fetch detailed profile. It specifies the resource (UK Companies House register) and actions (search, fetch), distinguishing it from sibling tools that cover 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 explicitly states the use case: 'For KYB, AML and supplier due-diligence agents.' It provides examples of when to search vs. fetch profile. However, it does not mention when not to use or alternative tools, but the context is sufficient for an agent.

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 distinction between 'invalid' and 'service unavailable' (national DB offline), and mentions pricing and payment method ($0.01 per call, x402 payment, USDC on Base mainnet). This goes beyond basic functionality, though it omits rate limits or authentication 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 concise at around 100 words, front-loaded with the core purpose, and structured with key details (returns, distinction, use cases, input format, 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?

For a simple tool with two parameters and no output schema, the description fully explains what it does, what it returns (valid/invalid, company name, address), and handles edge cases (unavailable). It is complete and clear.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds meaning by stating 'Input: 2-letter country code (EL for Greece) + VAT number' and 'VAT number without country prefix', which clarifies the expected format beyond the schema alone.

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

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

The description clearly states 'Validate an EU VAT number against the official EU VIES registry across all 27 member states' with specific verb and resource. It uniquely distinguishes this tool from siblings, as no other sibling tool performs VAT validation.

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 lists use cases: 'For invoicing, B2B onboarding, KYB and tax-compliance agents.' It also clarifies the distinction between 'invalid' and 'unavailable', providing context for when the result might be ambiguous. However, 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?

With no annotations, the description carries full burden. It discloses that it's powered by Jina Reader, costs $0.05 per call, and returns deduplicated markdown with source URLs. It does not mention rate limits or auth, but the pricing and behavior are 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 somewhat repetitive, with the first and second paragraphs echoing similar information. It could be more concise. However, it is front-loaded with the most important details.

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

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

Given no output schema, the description adequately explains return values (clean markdown with deduplicated source URLs) and provides pricing and use case context. It is complete for an agent to understand the tool's capabilities.

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

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

Schema coverage is 100%, but the description adds significant value with examples and clarifying conditional behavior (e.g., 'If set, scrape and extract this page as clean markdown instead of searching') and provides concrete example values for each parameter.

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

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

The description clearly states it performs web search and webpage extraction, returning clean markdown. It distinguishes itself from sibling tools which are mostly analysis or lookup tools, so no confusion.

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 tells the agent to use 'query' for search and 'url' for extraction, providing clear usage guidance. It does not explicitly mention when not to use it, 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, the description carries full burden. It discloses latency (<200ms), checks performed (OFAC, mixer, overspend), and pricing. It lacks details on side effects, error handling, or response format, but covers key behavioral traits for a risk screening 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 somewhat verbose, including pricing and marketing language (e.g., 'hosted spending guard an offline SDK cannot give'). It is front-loaded with core purpose but could be more 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?

No output schema is provided, and the description only mentions the return type (ALLOW/REVIEW/BLOCK) without detailing response structure or error behavior. For a tool with 4 parameters, more completeness about output and edge cases would be beneficial.

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

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

Schema description coverage is 100%, so the schema already documents each parameter. The description reinforces the purpose of parameters (e.g., 'expected_price' for overspend detection) but adds minimal new semantic meaning beyond the schema.

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

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

The description clearly states the tool's function: a pre-payment risk firewall that validates recipient, amount, and chain before sending an x402 payment, returning ALLOW/REVIEW/BLOCK. It lists specific checks like OFAC blocklist and overspend prevention, making the purpose highly specific and distinct.

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 instructs to use this tool before sending an x402 payment. It mentions preventing overpaying or paying bad addresses but does not explicitly contrast with sibling tools or provide when-not-to-use scenarios. However, the sibling list shows no direct alternative, so the guidance is adequate.

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

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

No annotations are provided, so the description carries full burden. It discloses the cost, payment method, output type (signed receipt), and input requirements. It does not contradict any annotations. However, it could mention potential rate limits or confirmation that the audit is read-only.

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

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

The description is somewhat repetitive, with the first paragraph covering all details and the second paragraph summarizing similar points. It could be more concise by merging the two. However, information is front-loaded and the structure is logical.

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 (multiple data sources, verdict, signed receipt), the description covers the main deliverables and inputs. The absence of an output schema is partially compensated by listing report components. It provides sufficient context for an agent to understand the tool's purpose and scope.

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

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

Schema coverage is 100%, and the description adds context to the parameters: 'seller' can be wallet or domain with examples, and 'depth' has clear options ('shallow' ~200 settlements, 'deep' ~500). This enriches the parameter meaning beyond the schema descriptions.

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

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

The description clearly states the tool performs a deep audit of x402/ACP sellers, producing a full report including settlement reputation, advertised endpoints, liveness, web reputation, and a verdict. It distinguishes itself as deeper than a pass/fail badge, and the verb 'audit' is specific and appropriate.

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 context ('before trusting it') and mentions pricing ($0.50 per call). However, it does not explicitly state when not to use or compare to sibling tools like agent_due_diligence or x402_seller_trust, providing clear but not exhaustive 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, the description fully discloses what the tool does: it provides a trust score (TRUSTED/CAUTION/AVOID) with confidence, based on on-chain data (settlement count, counterparties, wallet age, wash-trade/sybil signals) and a signed receipt. This covers behavior well.

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 front-loads the purpose and then adds details. It is moderately concise; each sentence adds value, though it could be slightly tighter.

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 2 parameters and no output schema, the description explains the trust score, inputs, and business context well. It lacks explanation of receipt format but is otherwise complete.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds context (e.g., depth options are 'shallow' or 'deep') but does not significantly enhance understanding beyond the schema.

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

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

The description clearly specifies the verb 'Score' and the resource 'x402 seller wallet', and states the action context 'BEFORE paying it'. It outputs a verdict with confidence, which distinguishes it from sibling tools like x402_payment_firewall and x402_seller_audit.

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 'before you pay' and provides a use case for vetting unknown endpoints. However, it does not give when-not-to-use or alternative tools, missing some guidance.

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