Firecrawl

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint, so the description adds value by detailing the Anthropic key pass-through and return format (score, confidence, signals). 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 two well-structured sentences with no redundancy. The first sentence captures the main action, the second provides additional details and use cases. Every word earns its place.

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

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

Despite no output schema, the description explains return structure (per-model score, confidence, signals, raw_response plus combined view). It covers input semantics, usage guidelines, and behavior, making it complete for the tool's complexity.

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

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

Schema coverage is 100%, but the description adds context: default model is free, _apiKey is passed through to Anthropic, and context helps disambiguate entities. This goes beyond the schema descriptions, justifying a 4.

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

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

The description clearly states the tool probes LLMs for knowledge about entities and scores visibility (0-100), specifying default model and optional Anthropic integration. It distinguishes from sibling tools like 'scan_competitor_ai_presence' by focusing on direct LLM probing.

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 (AI-marketing audits, pre-launch brand checks, competitive monitoring) and explains how to use the _apiKey for Anthropic probing. It does not specify when not to use or alternatives, but the context is sufficient for typical 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 already provide safety profile (read-only, idempotent). Description adds valuable context: 'routes to one of 3,336 tools across 747 sources' and 'returns structured answer with pipeworx:// citation URIs', which is 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?

Description is long but well-structured with key upfront message, bullet-like list of use cases, and examples. Every sentence adds value, though slightly verbose.

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

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

Given the tool's vast scope (3336 sub-tools), description provides comprehensive guidance on purpose, usage, and output format. No output schema needed since description clarifies 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 coverage is 100% and describes aliases. Description does not add parameter-specific meaning beyond examples, so baseline 3 applies.

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

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

Description clearly states tool routes factual questions to thousands of structured data sources and returns citations. Distinguishes itself from siblings like web search by explicitly preferring it for authoritative data.

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

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

Explicitly says 'PREFER OVER WEB SEARCH' and lists exact use cases (SEC filings, FDA data, news, etc.) with examples. Provides strong guidance on when to use without excluding other 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?

The description discloses numerous behavioral traits: resolver contract, parent event extractor, news fallback handling, low-confidence and closed market handling, spread warnings. These go far beyond the annotations (readOnly, idempotent, etc.), providing rich 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 long but well-structured with clear sections (CLASSIFIERS, FAN-OUT EXAMPLES, RESPONSE SHAPES). Every sentence adds value, though it could be slightly more concise. Still, it is organized for efficient parsing.

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

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

Given the tool's complexity, the description covers all major aspects: classifiers, fan-out scenarios, response shapes, resolver contract, parent event extraction, news fields, safety behaviors. Without an output schema, the description compensates fully, making it complete.

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

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

Schema coverage is 100% with detailed descriptions for all three parameters. The description adds additional context for include_raw regarding response sizes and for depth implicitly. Baseline 3, but the extra context raises it to 4.

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

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

The description clearly states the tool researches Polymarket bets by pulling Pipeworx data. It specifies input types (slug, URL, question text) and outputs (evidence packet, market-vs-model comparison). While it doesn't explicitly differentiate from sibling tools, the specificity of the purpose implicitly distinguishes it.

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 ('should I bet on X', 'what does the data say about Y', 'is there edge in Z') and provides extensive examples of fan-outs. It does not mention when not to use the tool or direct alternatives, but the context is 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?

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds behavioral details: off-calendar fiscal year fix, pipeworx:// citation URIs, sorting by primary metric. 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?

Single paragraph, front-loaded with purpose. Efficiently covers key details without wordiness. Could break into shorter sentences but overall well-structured.

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

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

Covers both entity types, data sources, output format (paired data + citation URIs), sorting behavior. No output schema, but description adequately explains return values. Sufficient for a complex tool.

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

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

Schema coverage is 100% with minimal descriptions. Description elaborates on parameter meaning: tickers/CIKs for company, drug names for drug, and constraints (2-5 items). Adds value beyond schema.

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

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

The description clearly states the tool compares 2-5 companies or drugs side by side with specific metrics (revenue, net income, etc.) and data sources (SEC EDGAR, FAERS/FDA). It distinguishes from sibling tools by noting it replaces 8-15 sequential lookups, making it a batch comparison tool.

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

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

Explicitly tells when to use: for 'compare X and Y', 'X vs Y', 'which is bigger', or rank-by-metric questions. Does not provide exclusion criteria but clear context makes usage obvious.

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 readOnlyHint, idempotentHint, destructiveHint. Description adds context about returning top-N tools with schemas ready to call, and positions it as a discovery step, which is consistent with annotations. 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?

Description is front-loaded with core purpose and then lists domains. It is somewhat lengthy but every sentence adds value. Could be slightly more concise without losing clarity.

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

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

Given no output schema, description explains what is returned (top-N tools with full schemas). It covers the tool's role as a discovery gateway. Lacks details on pagination or error handling, but adequate 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%, and description adds value by explaining aliases, examples, and default limit. It enhances understanding beyond the schema alone.

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

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

Description clearly states it finds tools by describing the task, lists many domains, and distinguishes from sibling tools by positioning itself as the first call for discovery. It explicitly says 'Call this FIRST' and contrasts with direct tool usage.

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

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

Description tells when to use ('browse, search, look up, discover') and when to call it first. It implies that if you already know the tool, you can call directly, but does not explicitly say when not to use.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds detailed return fields, data freshness notes (FY2025 vs FY2022), and potential soft-fail for patents, providing rich 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 thorough but somewhat lengthy. It is front-loaded with purpose and usage, but the postscript on patents and LEI adds detail that could be streamlined. Still, every sentence adds value.

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

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

Despite no output schema, the description enumerates return fields and limitations thoroughly. It covers all critical aspects for agent decision-making, making it highly complete for a complex aggregator tool.

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

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

Input schema has 100% description coverage. The description reinforces parameter meaning (ticker or CIK, zero-padded) and adds behavioral context (names not supported, use resolve_entity). This significantly aids correct invocation.

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

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

The description clearly states the tool retrieves comprehensive data about a US public company in one call, with specific use-case examples like 'tell me about X' or 'research Acme'. It distinguishes itself from sibling tools by noting it replaces up to 10+ individual pack calls.

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

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

Explicitly states when to use (user asks for company research) and when not to (names not supported, recommends resolve_entity first). Also notes API limitations like the sunset patents API, guiding the agent on fallback behavior.

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 destructiveHint=true and idempotentHint=true, and the description aligns by stating 'Delete'. Description adds valuable context about clearing sensitive data and relationships with other tools, surpassing what annotations provide.

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, action front-loaded, no wasted words. Efficient and direct.

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 simple one-parameter tool with no output schema, description fully covers purpose, usage guidance, and relationships with sibling tools.

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

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

Only one parameter 'key' with schema description 'Memory key to delete'. Description does not add meaning beyond the schema, but with 100% coverage and simple parameter, a baseline of 3 is appropriate.

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

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

Description clearly states 'Delete a previously stored memory by key', using a specific verb and resource. Explicitly distinguishes from sibling tools 'remember' and 'recall', ensuring no ambiguity.

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

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

Provides explicit when-to-use scenarios: 'when context is stale, the task is done, or you want to clear sensitive data'. Also advises pairing with related tools, offering clear context for appropriate 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?

Description adds context beyond annotations: it specifies that the tool fetches a page and extracts title/description/key links, consistent with readOnlyHint and idempotentHint. 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?

Three tight sentences: purpose, process, and use cases. No waste, front-loaded with key information.

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

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

Covers input, process, and output despite no output schema. Could mention error handling or validation, but overall complete for a simple generation 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 detailed descriptions for both parameters. The tool description does not add additional semantics beyond what is already in the schema, justifying baseline score of 3.

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

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

Description uses specific verb 'generate' and resource 'llms.txt file', clearly differentiating from sibling tools like 'scrape' or 'search'. It explains the entire process and 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?

Explicitly lists three use cases (indexing, drafting, auditing), but does not mention when not to use or alternative tools.

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

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

Annotations already declare readOnlyHint and idempotentHint, so the description does not add behavioral details beyond the obvious. It does not explain the crawling behavior, limits, or output format.

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

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

Single sentence, front-loaded, no superfluous words.

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

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

For a simple website mapping tool, the description is adequate but lacks details on result interpretation and usage constraints not in schema (e.g., crawl depth, timeouts).

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

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

Schema coverage is 100%, and the description does not add extra meaning to the parameters beyond what schema already provides.

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

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

The description uses a specific verb 'Discover' and clearly identifies the resource 'all URLs on a website'. It is distinct from sibling tools like scrape or search, which have different purposes.

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

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

No usage guidance is provided – no mention of when to use this tool vs alternatives, no prerequisites, no situational 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 are minimal (readOnlyHint=false, etc.). The description adds important behavioral context: rate limit of 5 per identifier per day, free usage, no quota consumption, and that signals affect roadmap. It does not contradict annotations. Lacks explicit statement on idempotency, but overall provides good 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 detailed but well-structured: purpose first, then usage guidance, then constraints. Every sentence adds value, but it could be slightly more concise (e.g., merging rate limit and free statements). Generally well-written and front-loaded.

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

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

Given the tool's simplicity (3 params, no output schema), the description covers all necessary context: what to provide, limitations, expectations (daily digests, roadmap impact). It fully equips the agent to use the tool correctly without missing information.

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

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

Schema description coverage is 100% (all parameters described). The description adds value by explaining the enum values for 'type' with concrete examples and caution about not pasting user prompts. It complements the schema without redundancy, though some repetition with the schema exists.

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.' The verb 'tell' and resource 'Pipeworx team' make it unambiguous. It distinguishes itself from sibling tools by focusing on feedback, not actions like search or scraping.

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 on when to use: for bug, feature, data_gap, or praise. It also specifies what not to do ('don't paste the end-user's prompt') and includes usage context (rate-limited, free, doesn't count against quota). This gives the agent clear decision criteria.

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

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

Discloses data source (CF analytics-engine), privacy (no PII), and caching (5min-1h). Annotations already mark as read-only, idempotent, non-destructive; description adds valuable extra 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?

Concise, well-structured, front-loaded with the main purpose. Every sentence adds value with no fluff.

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

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

Complete for a simple tool with one parameter and no output schema. Covers purpose, usage, behavioral details, and return value implicitly.

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 description for the single parameter. Description reinforces meaning but adds minimal new value; schema already does the work.

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

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

Description clearly states it returns top tools, top packs, and total call volume for recent windows. Distinguishes from siblings like discover_tools by focusing on trending data from other AI agents.

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 use cases and mentions caching behavior. Provides good context for when to use, though doesn't 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?

The description details behavioral aspects beyond annotations: monotonicity violations, partition-sum checks, Jaccard similarity filter, partition placeholder filter, and response structure (opportunities[] with specific fields). Annotations only indicate read-only, idempotent, open world; description adds substantial context 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 a dense paragraph that conveys all necessary information, but it could be more scannable with bullet points or clearer segmentation for the two modes. However, every sentence adds value, so it's not overly verbose.

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

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

Given the complexity of the tool (two modes, multiple filters, statistical checks) and the absence of an output schema, the description thoroughly covers the return type (opportunities array with gap_pp, suggested_trade, etc.) and all edge cases (partition filter, Jaccard similarity, placeholders). Nothing essential is missing.

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

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

Although the input schema has 100% description coverage, the tool description adds deep meaning: it explains that 'event' expects a slug or URL, 'topic' expects a seed question, and elaborates on the logic triggered by each parameter, far exceeding the terse schema descriptions.

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

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

The description clearly states the tool's purpose: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It specifies two distinct modes (event and topic), which distinguishes it from sibling tools like polymarket_edges and polymarket_kalshi_spread that likely focus on different aspects.

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

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

The description provides explicit guidance on when to use each mode: 'event' for a single event slug, and 'topic' for cross-event searches with a seed question. It explains that cross-event mode catches patterns missed by single-event mode, and mentions the Jaccard similarity threshold and partition filter conditions.

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

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

Annotations already declare read-only, idempotent, non-destructive. The description adds substantial behavioral details: response structure, edge calculation methodology, caching (1h at KV level), and diagnostics. 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?

The description is very long (multiple paragraphs) and front-loads the main purpose but then dives into extensive methodological details. While thorough, it is not concise and could be better structured for quick scanning.

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 (9 parameters, three segments, caching, diagnostics), the description covers all necessary aspects. It explains the response structure and filtering thoroughly, compensating for the lack of an output schema.

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

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

Schema coverage is 100% with detailed descriptions. The description adds value by explaining interactions (e.g., min_partition_leg_kelly vs min_kelly) and providing context for parameters like slippage_pp. Thus, baseline 3 is exceeded.

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 and returns opportunities where Pipeworx data disagrees with market price. It specifies the three segments and distinguishes from sibling tools like polymarket_arbitrage by focusing on disagreement with Pipeworx data.

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

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

The description provides usage context: 'Built for what should I bet on today' and explains when to apply filters (e.g., min_liquidity, max_spread_pp). It does not explicitly state when not to use the tool or compare to siblings, but the guidance is extensive.

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 read-only, idempotent, and non-destructive behavior. The description adds substantial behavioral detail: it explains that the tool detects non-equivalent bet shapes (via 'compatibility_warning'), temporal misalignment (via 'temporal_alignment'), and leg-pair comparison exclusions (via 'skipped_cross_type'). 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 densely packed but each sentence adds necessary information. It is front-loaded with the core purpose and modes. Minor redundancy could be trimmed, but overall it earns its length.

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

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

No output schema exists, so the description must explain return values. It thoroughly covers the response structure, including leg prices, spreads, safety fields, and temporal alignment. It also addresses edge cases like non-equivalent bet shapes. Complete for the tool's complexity.

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

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

The schema covers all three parameters with descriptions. The description adds value by explaining that 'topic' is a shortcut for pre-mapped macros, and that explicit tickers/slugs override the topic mappings. This contextualizes the parameters 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 computing the cross-venue spread between Kalshi and Polymarket for the same resolving question. It distinguishes from siblings like 'polymarket_arbitrage' by focusing on two specific venues and explicitly mentioning the unique behavior of comparing identical outcomes.

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 two modes: 'topic' for pre-mapped shortcuts and explicit tickers/slugs for custom pairings. It warns that pre-mapped topics often return 'compatibility_warning' and are not necessarily tradeable, guiding the agent on when to expect meaningful results.

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 and idempotentHint=true, so the description's claim of retrieval is consistent. Beyond annotations, it adds scoping details (anonymous IP, BYO key hash, account ID) and lifecycle context (pairing with remember and forget), which helps the agent understand the tool's behavior.

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

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

Three sentences with no redundancy. The first sentence immediately states the main action and modes, the second gives usage examples, the third adds scoping and sibling relationships. Every sentence is meaningful.

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

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

For a simple read tool with one optional parameter and no output schema, the description covers all necessary context: purpose, when to use, scoping, and relationship to siblings. Annotations provide the safety profile, and the description fills in the rest.

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

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

Schema coverage is 100% and the schema already describes the parameter 'key' including its optional nature and effect when omitted. The description echoes that information but does not add new semantic details beyond what's in the schema. Baseline 3 is appropriate.

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

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

The description clearly states the verb 'retrieve' and the resource 'values saved via remember', and distinguishes from siblings by explicitly mentioning the pairing with remember and forget. It also explains two modes: retrieving a specific key or listing all keys.

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 on when to use (to look up prior context) and how to use (omit key to list all). It also gives examples of typical stored data. However, it does not explicitly exclude situations where recall should not be used, but the pairings with remember and forget implicitly cover that.

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 readOnlyHint, openWorldHint, idempotentHint. Description adds extensive behavioral details: parallel sources (SEC, GDELT→GNews fallback, USPTO), soft-fail for PatentsView API sunset, return structure with citation URIs. 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?

Front-loaded with purpose and examples, then details sources, parameter format, return structure, and sibling alternative. Every sentence adds value. No redundancy or fluff.

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

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

No output schema, so description fully explains return format (grouped changes, total count, citation URIs). Covers prerequisites, source behavior, and fallback. Complete for a multi-source monitoring 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%, but description adds crucial extra context: for 'since' provides examples and typical usage ('30d' or '1m'), for 'value' explains ticker vs CIK, for 'type' confirms only 'company' supported. Adds meaning beyond schema.

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

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

The description clearly answers 'What's new with a company?' with examples like 'what's happening with X', and explicitly distinguishes from sibling tool 'entity_profile' which provides static profiles. The verb 'change-monitoring' and resource 'company' are specific.

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

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

Explicitly states when to use (monitoring updates) and when to use alternative ('Use entity_profile instead when you want the static profile...'). Also explains parallel fan-out to multiple sources and fallback behavior.

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

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

Discloses key behavioral traits beyond annotations: storage as key-value pair, scoping by identifier, and persistence differences between authenticated (permanent) and anonymous (24 hours) users. Annotations already indicate idempotent and non-destructive, and description adds context 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?

Four sentences, each earning its place: purpose, usage guidance, persistence behavior, and pairing with recall/forget. Front-loaded with the core function, no redundant words.

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

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

Given the simple schema (2 params, no enums, no nested objects) and annotations, the description fully covers purpose, usage, persistence, and relationships with sibling tools. No output schema needed as the action is straightforward save.

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 key (example formats) and value (any text). Description adds usage context with examples (subject_property, target_ticker) and clarifies that value can store findings, addresses, etc., reinforcing parameter semantics.

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

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

The description clearly states the verb 'Save data' and the resource 'to reuse later', specifying scope across conversations or sessions. It distinguishes from siblings by pairing with recall and forget, and provides concrete examples of what to store.

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 ('when you discover something worth carrying forward') and gives examples. Implicitly covers when not to use by focusing on valuable discoveries. Clearly pairs with recall for retrieval and forget for deletion, aiding 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 declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, idempotentHint=true. Description adds that the tool cascades through multiple lookup endpoints and replaces 2-3 manual lookups, providing valuable 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?

Well-structured: purpose first, then usage guidance, then detailed examples. A bit lengthy but each sentence adds value. Could be slightly more concise, but 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 complexity (two entity types, multiple identifiers, internal cascading), the description is thorough. Covers inputs, outputs, and citation URIs. No output schema, but return values are described adequately.

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

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

Schema coverage is 100%, but description adds meaning by explaining the two entity types and providing example inputs for the value parameter (e.g., 'AAPL', 'ozempic'). Enhances understanding beyond the schema's descriptions.

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

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

Clearly states the tool resolves user-spoken names to canonical identifiers. Specific verb 'resolve' and resource 'names to IDs'. Supported types and outputs explicitly listed. Distinguishes itself from sibling tools by focusing on identifier 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 says 'Use FIRST when you have a name but need an ID.' Provides clear context for use. Does not explicitly mention when not to use or name specific alternatives, but the purpose is unambiguous.

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, and non-destructive. The description adds that it internally probes each entity with `ai_visibility_check`, ranks by score, and returns score, confidence, and signal density – details beyond annotations that fully disclose tool behavior.

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

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

Three tightly packed sentences with no filler. The main action and key output features appear in the first sentence, making it immediately useful. 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?

Despite no output schema, the description covers input, internal process (probing with `ai_visibility_check`), and output structure (ranked list with score, confidence, signal density). All needed 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 coverage is 100% with descriptions for all 4 parameters. The description enriches understanding: clarifies `entities` ordering (first is subject), default model for `models`, conditional requirement for `_apiKey`, and effect of `context`. This adds significant 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 opens with a specific verb+resource ('Compare AI visibility across multiple entities side-by-side'), directly states the tool's function, and distinguishes it from sibling `ai_visibility_check` by noting it probes multiple entities.

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 frames the tool for competitive AI-marketing audits with a concrete question example. While it doesn't list when-not-to-use or alternatives to `compare_entities`, 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, destructiveHint) are consistent. Description adds granular behavioral detail: partial failures degrade gracefully, bundlephobia first measurement takes 5-30s, sources_failed field, and remaining data returns.

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

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

The description is detailed but not overly verbose; every sentence adds value. It could be slightly more structured, but it efficiently conveys a composite tool's behavior in one paragraph.

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

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

Despite no output schema, the description enumerates return fields (summary block, per-advisory, links, alternatives). It covers ecosystem scope, partial failures, timing, and fallback, making it complete for this 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 parameter descriptions. Description adds value by mentioning scoped packages (e.g., '@types/node') and default version behavior, providing context beyond schema.

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

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

The description explicitly states it's a composite check for npm packages, listing data sources (deps.dev, bundlephobia) and the returned fields. It clearly distinguishes from siblings, none of which are dependency scanners.

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 explicit when-to-use guidance ('is X safe / popular / small' or 'what does adding lodash cost me'), notes NPM-only limitation in v1, fallback for other ecosystems, and graceful degradation behavior.

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, openWorld, idempotent, and non-destructive hints. The description adds value by revealing JavaScript rendering and main-content-only extraction, which are key behavioral traits not captured by annotations.

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

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

The description is a single, front-loaded sentence that conveys the core purpose and key features without any extraneous words. Every element earns its place.

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

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

Given the 100% schema coverage, good annotations, and no output schema, the description is largely complete. It covers the tool's purpose and behavioral traits, though it could mention potential limitations (e.g., rate limits) for even fuller context.

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

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

Schema coverage is 100%, so the schema already describes all 4 parameters adequately. The description does not add new semantic information beyond the schema, resulting in a baseline score of 3.

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

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

Description uses specific verb 'scrape', identifies resource 'single URL', and specifies output 'clean markdown' with key traits (JS-rendered, main content only). This clearly distinguishes it from sibling tools like 'search' or 'map'.

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 when to use the tool (scraping a single URL for clean markdown content) but offers no explicit guidance on when alternatives like 'search' or 'map' are more appropriate, nor any 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 already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering safety and idempotency. The description adds 'optional page content' hinting at fetching page bodies, which is not in annotations. However, it lacks details on rate limits, API key implications, or response structure. 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 a single sentence of 35 characters with no extraneous words. It is maximally concise while conveying the core purpose and an optional feature. Every word earns its place.

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

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

For a simple 3-parameter tool with comprehensive annotations and 100% schema coverage, the description is nearly complete. However, since there is no output schema, the description should hint at return values (e.g., titles, URLs, snippets) or the 'page content' format. Its absence leaves minor ambiguity.

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

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

Schema coverage is 100%, so the schema already describes all three parameters adequately. The description adds no parameter-level details beyond the schema, merely restating the optional page content aspect. Baseline 3 is appropriate given high schema coverage.

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

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

The description 'Web search with optional page content' clearly states the tool's primary function (web search) and an additional capability (page content). It distinguishes itself from sibling tools like 'scrape' or 'scan_competitor_ai_presence' by being a general-purpose search, though not highly specific.

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

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

No guidance is provided on when to use this tool versus alternatives such as 'scrape', 'validate_claim', or 'bet_research'. The description does not mention scenarios, prerequisites, or exclusions, leaving the agent without context for 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 provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds significant value by detailing the return values (verdict types, actual value with citation, percent delta) and explaining the data source (SEC EDGAR + XBRL) and scope. 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 a single focused paragraph with no wasted words. It front-loads the core verb and quickly provides usage context, then details scope, output, and efficiency. Every sentence earns its place.

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

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

Given the single parameter, no output schema, and annotations, the description is fully complete. It specifies the output format (verdicts, actual value, citation, percent delta), the data source, and the supported claim domain, leaving no ambiguity for the 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?

With schema coverage 100%, baseline is 3. The schema describes the 'claim' parameter well. The description adds extra context about the type of claims (company-financial) but does not significantly enhance understanding beyond the schema.

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

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

The description clearly states the tool's purpose: fact-checking natural-language claims against authoritative sources. It provides specific verbs (fact-check, verify, validate, confirm/refute) and distinguishes itself by noting it replaces 4-6 sequential calls, setting it apart from siblings like 'search' or 'bet_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 tells when to use the tool ('when an agent needs to check whether something a user said is true') and gives example queries. It lacks explicit when-not-to-use instructions or alternatives among siblings, but the context is clear enough for the intended domain.

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