Boi Il

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds behavioral details beyond these: it requires an API key for Anthropic calls, passes it through to api.anthropic.com, and returns per-model JSON with specific fields. No contradictions with 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 four sentences, front-loaded with the main action and key details. Every sentence adds value: main function, default model, optional API key, return structure, and use cases. No wasted words.

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

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

Despite lacking an output schema, the description details the return format (per-model {score, confidence, signals, raw_response} + combined view) and the scoring scale (0-100). It covers inputs, outputs, and use cases adequately for a probing tool with good annotations.

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 essential context: default model is 'Workers AI Llama-3.3-70b (free)', how '_apiKey' is used, and that 'context' helps disambiguate common names. This adds significant 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 uses a specific verb ('probe') and clearly identifies the resource (LLMs knowledge about an entity) and the action (score visibility 0-100). It distinguishes from siblings by focusing on AI model visibility, which is absent in other tools like 'ask_pipeworx' or 'scan_competitor_ai_presence'.

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 usage contexts: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.' It does not provide when-not-to-use or direct alternatives, but the context is clear enough for an agent to infer appropriate scenarios.

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

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

Annotations (readOnlyHint, idempotentHint, etc.) are consistent with the description. The description adds valuable behavioral context: how it routes to 3,800 tools, fills arguments, and returns structured answers with citation URIs. No contradictions.

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

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

The description is concise yet comprehensive, front-loading the key directive ('PREFER OVER WEB SEARCH') and then listing domains and examples. A few more sentences could be trimmed, but overall every sentence adds value.

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

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

Given the tool's simplicity (one required parameter, no output schema), the description thoroughly covers purpose, usage, behavior, and expected output (structured answer with citations). It is complete enough for an AI agent to select and invoke correctly.

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

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

Schema coverage is 100%, with the description reinforcing the parameter's role ('natural language question') and providing aliases and example queries. The description adds meaning beyond the schema by specifying the kinds of questions suitable.

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: answering factual questions using authoritative structured data, with specific examples and domains (SEC, FDA, etc.). It distinguishes itself from web search by emphasizing structure and citations, and the detailed domain list differentiates it from vague search tools.

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

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

The description explicitly prefers this tool over web search for factual queries and provides trigger phrases ('what is', 'look up', etc.) and examples. While it doesn't list explicit exclusion criteria, the detailed domain coverage and examples give clear usage context.

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

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

Description adds behavioral context beyond annotations: it explains the refusal reasons, that answers are extracted solely from tool results, and the extra LLM cost. No contradictions with 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 well-structured and front-loaded with the core purpose. It is somewhat lengthy but every sentence adds value. Minor improvement could be made 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 the complexity of the tool (hallucination resistance, tool routing, refusal logic), the description covers return format and refusal reasons adequately. No output schema exists, but the description compensates by detailing the response structure.

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 3. The description lists multiple aliases for the question parameter but doesn't add additional meaning beyond the schema's own description. No further elaboration on parameter usage or constraints.

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

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

The description clearly states it's a 'Hallucination-resistant answer mode for high-stakes reads' and explains the routing and extraction process. It distinguishes itself from the sibling tool 'ask_pipeworx' by noting the extra LLM call and stricter answer sourcing.

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 guidance: 'Use whenever an answer will be quoted, cited, or acted on' and 'Prefer ask_pipeworx for casual lookups.' This clearly defines when to use and when not to use, referencing the alternative sibling 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?

Annotations (readOnly, idempotent, non-destructive) are consistent. Description adds extensive behavioral details: low-confidence resolution short-circuits, closed market handling, wide-spread warnings, resolution-rule risk parsing, and fan-out logic. Goes well beyond annotations.

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

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

The description is long but well-structured, starting with a concise summary followed by organized sections (classifiers, examples, response shapes, safety). Every sentence adds value, though some redundancy exists. Could be slightly more concise without losing quality.

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 comprehensively details return fields (market, analysis, evidence, resolver contract, parent event, news fields) and edge cases (low confidence, closed markets, wide spreads, cancellation rules). Covers all necessary context for an agent to use the tool effectively.

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

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

Schema covers all 3 parameters (100% coverage), but description adds critical context: market input formats, depth options, and include_raw impact. Provides examples and default values, clearly enhancing utility 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?

The description clearly states the tool researches Polymarket bets by pulling Pipeworx data in one call, using a specific verb and resource. Examples of inputs (slug, URL, question text) and use cases ('should I bet on X') make purpose unambiguous and distinguish it from sibling tools.

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

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

The description explicitly states when to use: for betting advice, data queries, or edge detection. It provides classifiers and fan-out examples, but does not directly contrast with siblings like polymarket_edges, leaving some implicit differentiation. Still, usage context is clear.

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

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

Annotations indicate readOnly, openWorld, idempotent, non-destructive. The description adds context about data sources (SEC EDGAR, FAERS), sorting by primary metric, citation URIs, and fiscal year handling, going beyond annotations without contradiction.

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 long but front-loaded with query patterns. Every sentence provides value, though minor trimming could be possible.

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 two entity types with different data, no output schema, and 2 parameters, the description thoroughly explains inputs, data sources, sorting, and output format (paired data + citations).

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 examples, entity-specific behaviors, and data source details, enhancing 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 starts with common query patterns, then clearly states the tool does side-by-side comparison of 2-5 companies or drugs. It specifies what data is pulled for each type and distinguishes from sequential lookups.

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

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

Explicitly states 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' It clearly defines the scope (2-5 entities) but doesn't explicitly mention alternatives like entity_profile for single entities.

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?

Beyond annotations (readOnly, idempotent, non-destructive), the description details output structure: verbatim evidence, confidence, source, fetched_at, stable citation, and explicit gaps[]. It also mentions parallel execution and expected latency (15-60s). No contradictions with 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 comprehensive but slightly verbose. It is well-structured with key information front-loaded (research in one call). Every sentence adds value, but it could be more concise by condensing some operational 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 fully explains the output format (findings packet with evidence, confidence, source, etc.). It covers prerequisites, usage alternatives, latency, and behavioral guarantees (never invents). Complete for a complex research tool.

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

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

With 100% schema coverage, the description adds value by explaining depth enum meanings (quick=3, standard=5, thorough=8) and the 'thorough' paid requirement. For 'question', it clarifies that broad/multi-part queries are acceptable, reinforcing the tool's decomposition purpose.

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 'Grounded multi-source research in ONE call,' with decomposition and parallel routing. It distinguishes from sibling ask_pipeworx by noting it handles broad/multi-part questions. The verb+resource is specific 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?

Explicitly advises when to use ('for broad or multi-part questions') and when not ('use ask_pipeworx for single lookups'). Also notes account requirements and paid plan for 'thorough' depth. This provides clear context for decision-making.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds that the tool returns top-N relevant tools with full schemas and examples, and that each result is directly callable. It does not contradict annotations and adds useful 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 concise with no wasted words. It front-loads the core purpose and provides necessary details about return value and usage in a well-structured manner.

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

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

Given no output schema, the description explains the return value clearly: top-N tools with names, descriptions, schemas, and examples, ready to call directly. It covers the limit parameter and provides complete context for a discovery 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 all properties described. The description adds meaning with natural language examples like 'analyze housing market trends' and explains that query accepts aliases. This goes beyond the schema by providing usage patterns.

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 finds tools by describing data or tasks, with specific verb 'Find tools' and resource 'by describing the data or task'. It distinguishes itself from sibling tools by positioning as the first step for discovery, not for direct answers, and lists many domains and use cases.

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

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

The description explicitly says 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This provides clear context for when to use. However, it does not explicitly state when not to use or list alternative tools, though the context implies it.

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

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

Annotations already indicate read-only, open-world, idempotent, non-destructive behavior. The description adds significant behavioral context: fans out across multiple sources, specifics on returns (e.g., recent filings with URIs, fundamentals sorted), and notes patent data soft-fails due to API sunset. No contradictions with 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 dense but well-structured, starting with example queries and then detailing sources and outputs. Every sentence provides value, though it is relatively long. Minor improvement could be trimming redundancy with schema descriptions, but it's concise for the complexity.

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

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

Without an output schema, the description fully explains what is returned (cik, company_name, filings, fundamentals, patents, news, LEI) and mentions the patent soft-fail. It covers inputs, limitations, and alternatives, making it self-contained for an AI agent.

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

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

Schema description coverage is 100%, and the description reinforces param details (ticker/CIK format, name not supported). However, it adds little beyond what's already in the param descriptions, such as the examples and the 'resolve_entity' referral. Adequate but not exceptional.

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 'full cross-source profile of a US public company in ONE parallel call,' supported by example queries and a list of output components. It distinguishes from siblings by noting it should be preferred over chaining single-pack lookups, and references resolve_entity for name 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?

Explicitly states when to use (holistic view of a US public company) and when not to (chaining single lookups, using names directly). Also provides alternative: use resolve_entity first if only a name is available. This offers clear guidance on tool selection.

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

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

Annotations already indicate readOnly, idempotent, non-destructive. The description adds value by specifying return fields (currentExchangeRate, currentChange, unit, lastUpdate) and noting unit quirks (e.g., JPY per 100). No contradiction with annotations.

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

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

Two sentences, front-loaded with purpose, then output details and examples. No wasted words.

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

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

Given single parameter, no output schema, description sufficiently covers all needed information: input format, output fields, and special unit handling. Complete for low-complexity tool.

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

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

Schema covers 100% of parameters with description. The description reinforces '3-letter ISO code' and provides examples, adding meaning 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 the tool returns the Bank of Israel exchange rate for a single currency vs ILS, lists output fields, and gives example currency codes. It differentiates from sibling 'exchange_rates' (plural) by implying single currency lookup.

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

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

The description does not explicitly state when to use this tool vs alternatives like 'exchange_rates' (plural) or 'interest_rate'. However, it implies use for single currency lookups via ISO code, which provides some guidance.

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

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

Annotations already mark readonly and idempotent. The description adds value by detailing exact fields (currentExchangeRate, currentChange, unit, lastUpdate) and explaining unit conversion ('per-1 rate = currentExchangeRate / unit').

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 efficient sentences, each earning its place: purpose, return fields, usage advice. No wasted words.

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

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

For a zero-parameter tool with no output schema, the description fully explains the return fields and behavior, making it self-sufficient.

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

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

No parameters; baseline is 4. The description goes beyond by explaining the output structure and unit logic, which is critical for correct usage.

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

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

Clearly states the tool returns all Bank of Israel exchange rates vs ILS, distinguishing it from sibling 'exchange_rate' which likely handles a single currency.

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

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

Explicitly says 'Use this for a snapshot of all available currencies,' implying when to use. Does not explicitly exclude alternatives, but context suggests 'exchange_rate' for single currency.

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

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

Annotations already declare destructiveHint=true and idempotentHint=true. The description adds 'Delete a previously stored memory' but does not elaborate on behavior for non-existent keys or error handling. No contradiction with annotations.

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

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

Two sentences: first states the action, second provides usage guidelines. No redundant or extraneous content. Front-loaded with essential purpose.

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

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

For a simple single-parameter destructive tool with annotations, the description covers purpose and usage. However, since there is no output schema, it does not explain return values or behavior for missing keys, which is a minor gap.

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

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

The only parameter 'key' is fully described in the input schema with 'Memory key to delete'. The description merely repeats 'by key', adding no extra 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 uses a specific verb 'Delete' and identifies the resource as 'memory by key'. It distinguishes from sibling tools by mentioning 'Pair with remember and recall', making the tool's unique function clear.

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

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

Explicitly states when to use the tool: when context is stale, task is done, or to clear sensitive data. Also references sibling tools for pairing, providing clear usage context.

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

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

Annotations declare readOnlyHint=true and destructiveHint=false, which are consistent with the description's process (fetches, extracts, emits). The description adds behavioral context: fetching the page, extracting title/description/key links, and outputting markdown format. No contradictions.

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

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

The description is concise with three sentences, front-loading the main action and then listing use cases. Every sentence adds value, 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 simplicity (2 params, 100% schema coverage, clear annotations), the description fully explains what it does, how it works, and the output format. No 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 both parameters are described in the schema. The description adds a clarifying example for 'url' ('e.g. https://example.com') but does not add new information for 'max_links' beyond existing default and max values. 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 generates a production-ready llms.txt file for any URL, specifying the verb 'generate', the resource 'llms.txt file', and context for AI crawlers. It distinguishes from siblings like ai_visibility_check by focusing on generating the specific file format.

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: getting a client's site indexed, drafting for own project, or auditing competitor's AI crawl view. While it lacks explicit 'when not to use' guidance, the positive use cases are clear and helpful.

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

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds value by listing the specific returned fields (currentInterest, nextInterestDate, lastPublishedDate), which is useful behavioral context beyond annotations.

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

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

The description is two sentences long, front-loaded with key information, and every sentence earns its place. No wasted words.

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

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

For a zero-parameter tool with comprehensive annotations, the description fully explains the output fields. Even without an output schema, it provides a complete picture of 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?

There are no parameters, so schema coverage is 100% trivially. The description does not need to add parameter semantics. Baseline 4 applies as the description adds no additional parameter info, which is acceptable.

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 the current Bank of Israel policy interest rate per annum, specifying the exact fields returned. This distinguishes it from sibling tools like exchange_rate, which deal with currency exchange.

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 retrieving the interest rate but does not explicitly state when to use it versus alternatives or provide any exclusions. Given the context of sibling tools, the usage is clear but not explicitly guided.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds value by specifying the returned fields and the optional include_inactive parameter, clarifying the scope to the caller's subscriptions.

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

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

Two sentences, front-loaded with purpose and return fields, no waste. Every sentence is necessary.

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 list tool with one optional parameter and no output schema, the description fully covers purpose, usage, and return fields. It is 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% for the only parameter, so the description does not need to add detail. It implies 'active' vs 'inactive' via the param name, but adds no additional 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 verb 'List' and resource 'the caller's active subscriptions' with specific return fields. It distinguishes from sibling tools like subscribe and unsubscribe by mentioning 'find an id to cancel'.

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 context: 'Use this to review what you're monitoring before adding more or to find an id to cancel.' It does not explicitly state when not to use or name alternatives, but the context is clear given 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?

Annotations are all false (no readOnlyHint, destructiveHint, etc.). The description adds key behavioral details: the tool sends feedback data, is rate-limited, and is free. It does not contradict annotations and provides context beyond what annotations alone convey.

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

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

The description is dense but highly efficient: every sentence delivers distinct information (purpose, usage, constraints, guidelines). No redundancy or filler. Front-loaded with core purpose.

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

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

Given no output schema, the description sufficiently covers all aspects: feedback types, usage context, format guidelines, rate limits, and quota impact. No gaps for an agent to misunderstand.

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 overall description further clarifies the intent and format of parameters (e.g., 'Be specific... 1-2 sentences typical, 2000 chars max'). It adds semantic value beyond the schema definitions.

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 ('Tell the Pipeworx team something is broken, missing, or needs to exist') and specifies four distinct feedback types (bug, feature, data_gap, praise) with one-sentence definitions. It distinguishes from all sibling tools, none of which are feedback-related.

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

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

Explicitly tells when to use each feedback type, what to avoid (don't paste end-user prompt), and provides constraints (rate-limited to 5 per identifier per day, free, doesn't count against quota). This gives clear guidance for tool selection and 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?

Annotations already declare read-only, open-world, idempotent, and non-destructive. Description adds value by stating cached (5min-1h), no PII, and data source (CF analytics-engine), offering behavioral context beyond annotations.

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

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

Five sentences, front-loaded with purpose, followed by use cases and technical notes. No redundant or unnecessary 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 no output schema, description adequately explains return values (top tools, packs, call volume) and format (pack, tool, count). Caching policy is noted. Complete for a simple query 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 the lone parameter with enum and description (100% coverage). Description adds extra nuance: 'Shorter windows surface what's hot right now; longer windows show steady-state demand.'

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 top tools, packs, and call volume over recent windows, with specific use cases. It differentiates itself from siblings by focusing on aggregate trending data from Pipeworx.

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 three concrete use cases (e.g., discovering hot data sources, confirming canonical tools, aligning usage). Does not mention when not to use, but context is clear enough for selection.

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

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

Adds substantial behavior beyond annotations: requires one of two parameters, details monotonicity and partition checks, semantic anchor (Jaccard similarity), placeholder filtering, fill check against CLOB depth, and response structure. Annotations provide only read-only, idempotent, open-world hints.

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

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

Front-loaded with the requirement. Structured with clear sections. Slightly verbose but all information is valuable for a complex tool; could be trimmed slightly 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?

Covers parameter requirements, mode selection, all checks, response details, fill check, and references to sibling. Lacks explicit description of error or empty-result behavior, but given no output schema, it is reasonably 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?

Despite 100% schema coverage, the description adds meaningful context: recommends event for specific markets with example slugs, explains topic mode with seed question examples, and clarifies parameter semantics beyond 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 finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks, with two explicit modes (event and topic). It distinguishes from siblings by referencing polymarket_fill_risk for custom sizing and detailing unique capabilities.

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 guidelines on when to use each mode (event for specific market, topic for cross-event scanning) and warns against trading when realizable_edge_pp ≤ 0. References polymarket_fill_risk for custom sizing but does not compare to all sibling tools like polymarket_edges.

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

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

Annotations declare read-only and idempotent. The description adds rich behavioral context: explains the three model families, output fields, cache behavior (1h KV-level), and exclusion of Fed bets from ranking. No contradictions.

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

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

Well-structured with purpose first, then segments, output fields, knobs, and response structure. However, it is verbose and could be more concise for an agent.

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

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

Given the tool's complexity (9 parameters, three segments, no output schema), the description thoroughly explains output fields, top-level structure, and diagnostics. Covers edge cases like Fed bets and cache behavior.

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 mentions 'knobs' but does not add new semantic details beyond schema. Adequate but not extra 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 scans Polymarket markets to return opportunities where Pipeworx data disagrees with market price, with a specific verb and resource. It distinguishes from siblings like polymarket_arbitrage by focusing on Pipeworx data and providing segmented output.

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 discovering betting opportunities without paging, but does not explicitly state when to use alternatives like polymarket_arbitrage. It provides context but lacks clear when-not guidelines.

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

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

Annotations already indicate read-only and idempotent. The description adds valuable behavioral context: history bounded by 60-day TTL, decay from daily closes not intraday, and snapshot gaps explanation. No contradictions.

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

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

The description is somewhat long but each sentence adds value. It front-loads purpose and provides structured output fields. Could be slightly more terse, but effectively informative.

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

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

Despite no output schema, the description fully explains the return structure (tracked, expired, snapshot_dates) and includes limitations (TTL, daily close basis). Everything needed for correct invocation is covered.

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 100%. Description adds default values (days=14, window='1wk'), clamp range for days, and clarifies window as 'snapshot family' with available options. This is helpful 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?

The description clearly states the tool's purpose: edge persistence and decay telemetry from daily snapshots. It answers the specific question 'how long has this edge existed and is it shrinking?' and contrasts fresh vs old edges, distinguishing it from sibling tools like polymarket_edges.

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 guides usage by explaining what the tool answers, but it does not explicitly state when not to use it or name alternative tools. The context is clear: use this for historical edge persistence analysis, but lacks explicit exclusions.

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

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

Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false) are fully consistent with the description. The description adds behavioral context beyond annotations: it is a simulation/check that walks the order book ladder, returns fill estimates and a verdict, and warns about unhedged risk. It does not contradict any annotation.

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

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

The description is long but well-structured with clear sectioning (SINGLE-MARKET:, BASKET:) and bold for important warnings. Every sentence provides value, though some repetition could be trimmed. It is front-loaded with the key verb 'check' and 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?

Despite no output schema, the description thoroughly covers return values for both modes (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict for single-market; theoretical_sum, realizable_sum, capture_ratio, profit_usd, per-leg fill detail, thin_legs, max_clean_notional_usd, forced_directional_risk for basket). It also warns about thin books and unhedged directional risk, making the tool fully self-contained.

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 significant meaning: explains the difference between single-market and basket modes, default values for side and size_usd, interpretation of size_usd (spend vs proceeds vs settlement notional), and the auto behavior for side in basket mode. This goes well beyond the schema.

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

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

The description clearly states the tool's purpose as a 'Realizable-vs-theoretical edge check against live CLOB order-book depth' and explicitly distinguishes two modes (single-market and basket) with specific outputs. It also differentiates from sibling tools by stating 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500'.

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

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

The description provides clear when-to-use guidance: before acting on arbitrage signals or edges trades above $500. It explains prerequisites (market or event) and warns about consequences of not using it (partial basket fills leading to unhedged directional position). It does not explicitly list when not to use but implies small safe trades may not need 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?

Beyond readOnlyHint and idempotentHint annotations, the description explains internal logic: compatibility_warning triggers in two distinct scenarios, temporal alignment checks, and counters for skipped cross-type/subtype comparisons. This provides deep behavioral transparency without contradicting 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 well-structured with clear sections for modes, response, and safety fields. However, it is somewhat verbose (e.g., detailed explanation of compatibility_warning cases). It front-loads the core purpose, but some repetition 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, the description fully explains the response structure (leg-by-leg prices, matched spread, top_spreads_pp, safety fields) and covers edge cases (compatibility_warning conditions, temporal alignment). It leaves no major gaps in understanding.

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 good descriptions. The description adds further meaning by listing the pre-mapped topic values, explaining that explicit parameters override topic-mapped sides, and providing usage examples. This adds value 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 tool computes cross-venue spreads between Kalshi and Polymarket for the same question, distinguishes two modes (topic and explicit), and differentiates from siblings like polymarket_arbitrage by focusing on spread calculation between venues.

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

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

The description provides explicit guidance: use topic mode for 10 pre-mapped macros, or explicit mode for custom pairings. It warns that most pre-mapped topics currently return compatibility_warnings, advising that pre-mapped ≠ tradeable. This helps the agent decide when it's appropriate to use.

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

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

Annotations already provide readOnlyHint, idempotentHint, destructiveHint. The description adds value by explaining scoping ('Scoped to your identifier') and the behavior of omitting the key ('omit the key argument to list all saved keys'). No contradiction.

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

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

Three sentences, front-loaded with the core function, no wasted words. Every sentence adds essential information: what it does, when to use it, and its scope.

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

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

With one optional parameter, no output schema, and comprehensive annotations, the description fully covers the tool's behavior, scope, and relationship to siblings. It's complete for an agent to use correctly.

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

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

Schema coverage is 100% with a parameter description. The tool description adds meaning by explaining the omission behavior (list all keys) and giving examples of what keys might represent (ticker, address, notes), which complements 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 'Retrieve a value previously saved via remember, or list all saved keys', with a specific verb-resource pair. It distinguishes from siblings like 'remember' and 'forget' by naming them.

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

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

The description provides clear usage context: 'Use to look up context the agent stored earlier... without re-deriving it from scratch' and mentions scoping and pairing with remember/forget. It doesn't explicitly state when not to use, 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?

Annotations declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description accurately describes the optional mutating side effect of mark_read (flags events as read), which goes beyond the annotations. It does not contradict any annotations. The description provides useful behavioral context beyond what annotations alone convey.

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 (4 sentences) and front-loaded with the core purpose. Each sentence adds necessary detail without unnecessary words. The structure efficiently communicates purpose, return fields, filtering, side effects, and alternative access.

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 5 parameters and no output schema, the description adequately explains what the tool returns (source, citation_uri, raw payload) and how filtering works. It also mentions polling suitability and an alternative REST endpoint, which provides a complete picture for agent 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 parameters are already documented. The description adds significant meaning: it explains the effect of mark_read ('flag returned events read so the next call only shows newer ones'), gives an example of type filter ('sec_8k'), and indicates that since expects an ISO timestamp. This adds value 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 'pulls fired events from your subscription feed' and lists the return fields. It distinguishes this from other tools by mentioning the alternative GET endpoint for scripts, though it does not explicitly contrast with sibling tools. The verb 'Pull' and resource 'fired events' are specific and unambiguous.

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

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

The description explains when to use the tool (to get recent alerts, filter by type/time, mark read) and that polling works fine. It mentions an alternative access method (GET endpoint), providing some context. However, it does not explicitly state when not to use this tool or name alternative sibling tools.

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

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

Annotations already declare it as read-only and idempotent. The description adds rich behavioral details: fan-out to multiple sources, fallback logic between GDELT and GNews, soft-failure for USPTO, and structured output format. No contradictions.

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

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

The description is front-loaded with example queries, then explains the mechanism, input details, output shape, and disambiguation. Every sentence is informative and earns its place, with no superfluous text.

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 sources, fallback, parameter formats) and no output schema, the description comprehensively covers all aspects: input guidance, source behavior, return structure, and comparison to siblings.

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

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

Schema coverage is 100%, and the description adds further meaning: 'since' accepts ISO dates or relative shorthand with recommended values, 'value' can be ticker or CIK. This enhances the schema's information.

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 as a 'change feed for a company in the last N days/weeks/months' with specific sources. It distinguishes from the sibling 'entity_profile' tool, ensuring the agent knows when to use this one.

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 usage examples and directly mentions the alternative 'entity_profile' for static profiles. The description gives clear context for when to use this tool versus alternatives.

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

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

Annotations already indicate idempotentHint=true and destructiveHint=false. The description adds behavioral context: storage is scoped by identifier, authenticated sessions persist indefinitely, anonymous sessions last 24 hours. It does not contradict annotations.

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

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

The description is concise at around 70 words, front-loading the core purpose and then providing necessary details. Every sentence contributes to understanding, though it could be slightly more structured.

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

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

Given the tool's simplicity (2 required params, no output schema), the description covers the essential aspects: purpose, usage, storage behavior, and relationship to siblings. It is sufficiently complete for effective tool selection.

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

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

With 100% schema coverage, the schema already describes both parameters. The description adds value by providing example key patterns (subject_property, target_ticker, user_preference) and clarifying that value can be any text, enhancing the agent's 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: saving data for reuse across conversations or sessions. It gives specific examples (resolved ticker, target address, user preference) and differentiates from sibling tools by mentioning pairing with recall and forget.

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 provides clear guidance on when to use the tool ('when you discover something worth carrying forward') with concrete examples. It also explains the scope (by identifier) and persistence differences (authenticated vs anonymous). However, it does not explicitly 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?

Annotations already declare readOnlyHint, idempotentHint, and nondestructive behavior. The description adds value by detailing internal cascading lookups and specific return structures (ticker, CIK, RxCUI, citation URIs), which aids agent understanding beyond annotations.

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

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

The description is front-loaded with examples and a clear purpose, and every sentence provides necessary detail. It is slightly longer than minimal but efficiently packs information without redundancy.

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

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

Given the absence of an output schema, the description fully explains what the tool returns for each entity type, including citation URIs. It also notes internal cascading lookups, providing complete context for the agent to interpret results correctly.

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

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

Schema coverage is 100%, but the description substantially enriches both parameters: for 'type' it lists supported values with details on what each returns, and for 'value' it specifies accepted formats (ticker, CIK, name; brand or generic name). This goes well 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?

The description clearly states the verb (resolve) and resource (entity names to canonical IDs), provides concrete examples ('What's the ticker for...'), and distinguishes from siblings by emphasizing ID resolution rather than profiles or comparisons.

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 explicitly says 'Use FIRST whenever you have a name but need an ID,' establishing clear context. However, it does not specify when NOT to use it or name alternatives, leaving some ambiguity against sibling tools like entity_profile.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds that it probes each entity, ranks by score, and returns a ranked list with score, confidence, and signal density per entity, which goes beyond the annotations.

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

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

Three sentences that are front-loaded with the core action. No extraneous details; every sentence adds value.

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

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

No output schema exists, but description clearly states the return type (ranked list with score, confidence, signal density). It covers the main behavioral aspects. Could mention edge cases or errors, but given the tool's simplicity and annotations, it's sufficient.

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

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

Schema coverage is 100%, so the schema documents all parameters. The description adds meaning: entities parameter expects first entry as subject, context disambiguates common names, and models notes requirement for Anthropic API key if anthropic is included.

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 compares AI visibility across multiple entities side-by-side, probes each with ai_visibility_check, and ranks them. This differentiates it from siblings like ai_visibility_check (single entity) and compare_entities (generic 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?

Provides a concrete use case ('competitive AI-marketing audits') and an example question. While it doesn't explicitly list when not to use or compare to all siblings, it gives clear context for when this tool is appropriate.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint true, and destructiveHint false. The description adds details about fanning out to external services, potential delays (5-30s for bundlephobia first measurement), and graceful degradation with sources_failed. No contradictions.

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

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

Description is dense but well-structured, with main purpose first, usage guidance, return details, and limitations. Every sentence adds essential information 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?

Despite no output schema, the description thoroughly explains the return format including summary fields, advisory details, links, and alternative versions. Annotations cover behavioral aspects, making the definition complete for agent 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% with clear descriptions for both parameters. The description adds context about default version behavior and scoped package support, providing marginal added value 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 defines the tool as a composite check for npm packages, combining data from deps.dev and bundlephobia to answer questions about safety, popularity, and size. It distinguishes itself from sibling tools by specifying its unique functionality.

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

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

Explicitly states when to use this tool (when an agent asks about package safety, popularity, size, or cost of addition) and when not to use (non-NPM ecosystems, directing to deps.dev directly). Also notes partial failure handling.

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

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

Description adds significant behavioral context beyond annotations: embedding model (BGE-base-en), similarity metric (cosine), window size (500-char overlapping), character limits (200K chars), and truncation behavior. Annotations already indicate read-only and idempotent nature, which is consistent.

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 well-structured with a clear first sentence, followed by usage context and technical details. While slightly longer, each sentence serves a purpose and no extraneous content exists.

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 core functionality, usage, technical details, and outputs. Since no output schema, description explains return includes offsets and scores. Could mention handling of case sensitivity or edge cases, but 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 already has 100% description coverage. Description enhances by specifying max 200K chars for text, providing example queries, and noting default limit of 5. This adds meaningful context without redundancy.

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 semantic search inside a fetched record, with specific details about returning top-N passages, character offsets, and similarity scores. It distinguishes itself from siblings like ask_pipeworx_grounded by being the retrieval component.

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

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

Explicitly says 'Use when the record is too big to cram into the prompt' and provides pairing guidance with ask_pipeworx_grounded. Also mentions it saves context, making when-to-use very 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?

The description contradicts the annotations: it implies a new subscription is created each call (returns a new id) while annotations set idempotentHint=true, which suggests safe retries. Additional behavioral details are given (OAuth requirement, SMS cap, webhook auto-disable), but the idempotency contradiction undermines 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 front-loaded with the core purpose and is highly informative, though somewhat lengthy. It could benefit from bullet points for the type-specific details, but it remains efficient and actionable.

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

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

The description covers prerequisites (OAuth account), all subscription types, delivery channels with constraints, and webhook verification. It lacks explicit mention of rate limits on subscription creation or details on the return object beyond id, but overall it is comprehensive.

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

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

The description adds substantial meaning beyond the input schema, with detailed examples for each type and sub-parameters of delivery. Although schema coverage is 100%, the description enriches understanding with concrete use cases and constraints.

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

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

The description clearly states the tool's purpose as creating a proactive monitoring subscription to a live-data event stream and specifies it returns the new subscription id. It distinguishes from sibling tools like 'recent_alerts' and 'list_subscriptions' by emphasizing proactive, persistent subscriptions.

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

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

The description provides clear context for when to use this tool, listing supported subscription types, required OAuth account, and delivery options. It does not explicitly state when not to use it (e.g., for one-time queries), but the details are sufficient for correct selection.

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

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

Annotations already cover safety (readOnly, idempotent, non-destructive). Description adds functional behavior: returns example questions with tool calls, no contradictions.

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

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

Well-structured with trigger phrases and clear sections, though slightly lengthy. Most sentences add value.

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

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

Complete given complexity: explains return structure, usage, multiple trigger phrases, and no output schema needed as description covers return type.

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 100% of parameters; description adds context about topic focusing on a category, but not significantly beyond schema. Baseline 3 with slight addition.

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 is an onboarding entry point that returns category-bucketed example questions with tool+argument shapes, distinguishing it from siblings like ask_pipeworx and discover_tools.

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

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

Explicitly advises to use this tool first when unsure about Pipeworx's capabilities or to learn meta-tools, and explains optional topic parameter. No direct 'when-not' but context is clear.

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

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

Annotations indicate mutation (readOnlyHint=false) but not destructive (destructiveHint=false). Description adds key detail: 'deactivated (not deleted)', preserving historical events. No contradiction with annotations.

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

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

Two sentences, no fluff. Purpose, constraint, and side effect all front-loaded. Every sentence earns its place.

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

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

For a simple tool (1 param, no output schema), description is complete: action, id source, ownership rule, and deactivation behavior. No 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 100% with description for the single 'id' parameter. Description mentions 'by id' and links to subscribe, but does not add meaning beyond schema. Baseline 3 is appropriate.

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

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

Description clearly states 'Cancel a subscription by id' – specific verb and resource. Context about ownership and deactivation distinguishes it from sibling tools like subscribe and list_subscriptions.

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?

States ownership enforcement ('only cancel your own subscriptions'), giving clear usage boundaries. Does not name alternatives but implies when not to use. Deactivation note adds helpful 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?

Annotations already declare readOnly, idempotent, openWorld, non-destructive. The description adds key behavioral details: it replaces 4-6 sequential calls, returns verdict types (confirmed, refuted, etc.), and includes citation format. No contradictions.

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

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

The description is moderately long but well-structured with front-loaded examples. Every sentence serves a purpose, explaining intent, usage, domain, and output. Could be slightly tighter but overall 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 the single simple parameter and no output schema, the description covers all essential aspects: purpose, domain, output format, and behavioral efficiency. It is complete for the tool's complexity level.

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

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

Only one parameter with 100% schema coverage. The description adds value by specifying that the claim should be natural-language and provides examples, as well as limiting the supported domain to company-financial claims. This goes beyond the schema's minimal description.

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

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

The description uses user-intent phrases like 'Is it true that...' and explicitly states 'natural-language claim verification against authoritative sources.' It clearly distinguishes this from sibling tools by specifying its unique function (verification vs. search or research).

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

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

The description explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct.' It also scopes the domain to company-financial claims. However, it does not include explicit when-not-to-use guidance, though 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.