gamedeals

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

Annotations already cover readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description goes beyond by adding cost/ownership details ('BYO key — you pay Anthropic directly'), the default model (Workers AI Llama-3.3-70b free), and the per-model return structure. 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 four sentences, front-loaded with the primary function, and each sentence contributes: purpose, default/optional model behavior, return format, and use cases. No fluff or repetitive content.

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

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

Despite the lack of an output schema, the description explicitly lists the per-model return fields (`{score, confidence, signals, raw_response}`) and mentions a combined view, covering the agent's need to interpret results. It also explains the optional key and model selection logic. Minor omissions like error conditions or rate limits are not critical given the 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 description coverage is 100%, with thorough parameter descriptions including supported values and examples. The tool description adds marginal value by naming the default model and clarifying the _apiKey cost implication, but these are minor augmentations to an already self-documenting 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+resource: 'Probe one or more LLMs for what they know about a business / brand / product / topic' and states the scoring output ('visibility (0-100) per model'). It clearly distinguishes itself from siblings like 'ask_pipeworx' (single-entity Q&A) and 'scan_competitor_ai_presence' (competitor-focused) by emphasizing cross-LLM visibility scoring for any entity.

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

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

The description provides explicit use cases: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.' It doesn't name alternative tools or exclusion conditions, but the context is clear enough for an agent to select this tool over the listed siblings, especially with the noted free default model and optional Anthropic probing.

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, so safety and idempotency are covered. The description adds transparency about the routing mechanism, the citation format (pipeworx:// URIs), and the tool's non-hallucinatory and structured nature. It could be improved by mentioning any latency or limits for complex queries, but overall it's strong.

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 most critical instruction ('PREFER OVER WEB SEARCH') and proceeds logically: what it does, with concrete examples, then how to decide among siblings. It is comprehensive but not bloated; each sentence serves a purpose. The only minor issue is that the list of sibling tools and context makes this a long response, but the description itself is well-structured and not verbose.

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

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

Given the tool has no output schema, the description compensates by explaining the return format (structured answer with pipeworx:// citation URIs). It covers all essential aspects: purpose, routing, alternatives, and examples. For a tool of this complexity (routing to 5,563 tools), the description is remarkably complete, leaving no critical gaps for an AI agent to misunderstand usage or expectations.

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%, meaning the input schema already documents all 6 parameters (including aliases). The description goes beyond by explaining the overall purpose of the 'question' parameter and showing usage context through examples. It does not add semantic details for each alias (like 'q', 'text') but they are already explained in the schema, so the description effectively complements the schema 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 the tool's purpose: answering factual questions with authoritative structured data via routing to 5,563 tools. It specifies the verb 'routes' and the resource 'questions about current or historical data'. It distinguishes itself from siblings (like ask_pipeworx_grounded and deep_research) and even from web search, making it a clear default entry point.

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

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

The description explicitly tells when to use the tool ('PREFER OVER WEB SEARCH for questions about...', 'START HERE for most questions'), when to use alternatives ('Step up only when needed: for a hallucination-resistant single answer... use ask_pipeworx_grounded; for a broad/multi-part question... use deep_research'), and provides extensive examples of appropriate queries. It also sets clear expectations for excluding breaking news or speculative topics.

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 as false. The description adds valuable context: that it is a beta with experimental routing, that no candidate is active currently, and that it is a full working router (no fallback). This enriches the agent's understanding 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?

The description is three sentences that efficiently convey the beta nature, current state, and usage guidance. It is front-loaded with the key information and avoids unnecessary fluff, though it could be slightly more compact by merging the first two sentences.

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 is a router with no output schema, the description explains the beta status, current active candidate, how to use it, and the purpose of comparing results. It references the sibling ask_pipeworx for response shape, which is sufficient context. However, it does not describe the output format independently, which would be helpful if the sibling is not well-documented.

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 6 parameters documented as aliases for the 'question' string. The description does not add any new parameter semantics beyond what the schema provides, so a baseline score of 3 is appropriate.

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

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

The description clearly states it is a beta version of ask_pipeworx, a universal router, and distinguishes it from the stable sibling by noting it has experimental routing improvements. The verb 'ask' combined with the resource 'pipeworx' and the beta status make the purpose specific and unambiguous.

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

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

The description explicitly says 'Use it exactly like ask_pipeworx when you want the newest routing' and explains that it currently matches the stable version. It provides context for when to use it versus the stable router, though it does not explicitly state when not to use it (e.g., for production-critical tasks).

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds rich behavioral detail beyond annotations: the tool routes like ask_pipeworx, then extracts answers exclusively from tool results, returns structured responses with evidence and explicit refusal reasons (not_in_source, no_tool_match, etc.), and mentions the additional LLM call cost. 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?

Five sentences, each serving a distinct purpose: purpose definition, process explanation, return format (success/refusal), usage guidance, and cost trade-off. No fluff, front-loaded with key information, and 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 explicitly defines the return structure for both success and refusal cases, including refusal reasons. It covers purpose, behavior, usage, parameters (via aliases), and cost implications. For a complex routing tool with high stakes, this is fully 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 has 6 parameters (5 aliases + question) with 100% description coverage. The description does not add new parameter-level semantics beyond what the schema provides; it only implies arguments are filled automatically. Baseline 3 is appropriate when schema covers all parameters.

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

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

The description clearly states it is a 'hallucination-resistant answer mode for high-stakes reads', with a specific verb (extracts answer using ONLY tool result) and resource (routing across 5,563 tools and 1462 sources). It explicitly distinguishes from sibling 'ask_pipeworx' by noting the extra LLM call and use case.

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 guidance: 'whenever an answer will be quoted, cited, or acted on' and lists example domains (financial verdicts, legal claims, etc.). Also gives a clear when-not-to-use: 'prefer ask_pipeworx for casual lookups' with a cost rationale. This fully covers usage context and 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?

The description goes far beyond the annotations by detailing resolver confidence levels, low-confidence short-circuiting, market_closed_or_inactive status, illiquid/spread warnings, news fallback on rate limits, and resolution-rule risk with cancellation rules (refund_50_50, etc.). It explains exactly how the tool behaves in edge cases and what fields are suppressed. This is rich behavioral context well beyond the basic readOnly/idempotent 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?

The description is long but exceptionally well-structured, using labeled sections (CLASSIFIERS, FAN-OUT EXAMPLES, RESPONSE SHAPES, RESOLVER CONTRACT, etc.) and front-loading the core purpose in the first sentence. Every paragraph adds necessary context for a complex tool. It is not maximally concise — some examples could be trimmed — but the structure makes it scannable and earns each sentence.

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 three parameters, no output schema, and many edge cases, the description is remarkably complete. It covers response shapes (result.market, result.analysis, result.evidence), status codes (low_confidence_match, market_closed_or_inactive), tradeability warnings, parent_event extraction, news fallback mechanics, and cancellation-rule risk. The agent has everything it needs to invoke the tool correctly and interpret results, even without 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%, so the baseline is 3. The description adds valuable semantics beyond the schema: it explains the 'depth' default (thorough) and the 'include_raw' size implications ('keeps responses under ~20KB' vs '50KB-500KB'), and clarifies that the market param can be a slug, URL, or question text (already in schema but reinforced). These details help agents choose parameter values wisely.

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

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

The description states a specific verb and resource: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It clearly distinguishes the tool from siblings like polymarket_edges or deep_research by focusing on a single user-specified market and returning an evidence packet with market-vs-model comparison. The scope ('one call', resolves market, fans out) is precise.

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 it: 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z".' It also provides concrete fan-out examples for different bet types, giving context for applicability. However, it does not explicitly name alternatives or state when NOT to use it (e.g., 'for scanning many markets, use polymarket_edges'), so it misses the 'explicit when-not/alternatives' bar for a 5.

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

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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description reveals concrete behavioral traits: data sources (SEC EDGAR/XBRL for companies, FAERS for drugs), specific metrics pulled (revenue, net income, cash, long-term debt; adverse-event counts, approval counts, trial counts), handling of off-calendar fiscal years, result sorting by primary metric, and return format (paired data + citation URIs). This is rich context well beyond the structured 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-organized, starting with example queries, then the core comparison action, then type-specific details, sorting behavior, and return format. Every sentence adds value; no filler or repetition. The length is justified by the tool's complexity, and the structure makes it scannable.

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

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

Despite having no output schema, the description covers what is returned (paired data + pipeworx:// URIs), how results are sorted (by primary metric), data sources, and edge cases (off-calendar fiscal years). It also communicates the scope (2–5 entities) and efficiency (replaces 8–15 lookups). This is complete enough for an agent to select and invoke the tool correctly, especially with the supportive 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?

The schema provides only enum and array constraints, but the description adds crucial meaning: for type='company', it fetches latest 10-K financials; for type='drug', it pulls FAERS and FDA trial data. It also explains that values are 2–5 companies/drugs and how the primary metric affects sorting. This adds far more than the bare schema descriptions, fully compensating for the 100% schema coverage and enriching both parameters.

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

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

The description explicitly states the tool performs side-by-side comparisons of 2–5 companies or drugs in a single parallel call, with the verb 'compare' and clear target entities. It distinguishes itself from sequential single-pack lookups and provides concrete example queries ('X vs Y', 'which is bigger'), making the purpose unmistakable.

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

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

The description gives explicit when-to-use guidance: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities' and lists relevant query patterns. It also mentions that it replaces 8–15 sequential lookups, explaining the efficiency benefit. This clearly directs the agent to prefer this tool for multi-entity comparisons and to use single lookups otherwise.

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 include readOnlyHint, openWorldHint, idempotentHint, and destructiveHint (false). The description adds significant behavioral context beyond these: account requirements (free vs paid for 'thorough' depth), expected latency (15-60s, up to ~90s), the structure of the findings packet (verbatim evidence, confidence, source, fetched_at, citation_uri, gaps[], contradictions[]), that it never invents findings, the hop field, and that large records are semantically excerpted. No contradictions with annotations; instead, it enhances transparency.

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

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

The description is somewhat lengthy but front-loaded with the most critical information (account requirement, alternative, and core purpose). Every sentence adds specific details (latency, depth differences, citation URIs, gap behavior). However, the density of technical details (hop field, gap recovery, contradictions) makes it slightly dense, and could be streamlined without losing clarity. It earns its place but is not minimalist.

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 (2 parameters, no output schema, many siblings), the description is exhaustive. It covers: preconditions (account), alternatives (ask_pipeworx), behavioral nuances (no invention, gap recovery, contradictions, citation fetchability), depth semantics, latency expectations, return packet structure, and how it differs from other search tools. With no output schema, the burden on the description is high, and it fully addresses the agent's needs for selection and invocation confidence.

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

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

Schema description coverage is 100%, so the baseline is 3. The description provides rich context for the 'depth' parameter beyond enums (e.g., 'quick=3...standard=5...thorough=8...gap-recovery hop...contradictions[] scan'), and clarifies that 'question' should be in natural language and that broad/multi-part is fine. While this adds value, the schema already covers both parameters adequately with descriptions, so the additional benefit is moderate.

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

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

The description starts with a specific verb ('Ground...research') and resource ('Pipeworx's 1462 STRUCTURED data sources'), clearly distinguishing this tool from the sibling ask_pipeworx (open-web/news search) by stating that deep_research is a multi-source, parallel research tool for structured data. It explicitly contrasts with open-web search and siblings, addressing the differentiation criterion.

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 this tool vs alternatives: 'Best for broad/multi-part questions over structured data...', and provides clear exclusions: 'For BREAKING or colloquial CURRENT-NEWS /...prefer ask_pipeworx' and 'For a single lookup use ask_pipeworx'. It also warns that if not signed in, to use ask_pipeworx instead. This provides comprehensive usage context, including alternatives and 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 readOnly, idempotent, and non-destructive behavior. The description adds valuable behavioral context: it returns top-N most relevant tools with full schemas, making results directly callable without a second lookup. This goes beyond annotations by explaining the output's actionability.

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 ('Find tools by describing the data or task') and follows with usage context, domain list, and return value details. The domain enumeration is lengthy but informative; every sentence adds value without being 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?

Despite lacking an output schema, the description explains what the tool returns (tool names, descriptions, full schemas) and that results are directly callable. This is sufficient for a discovery tool. It could mention pagination but the `limit` parameter covers that 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?

The input schema covers 100% of parameters with descriptions and examples, including aliases for `query`. The description doesn't add new parameter semantics but reinforces that the query is a natural language description of data/task. Baseline 3 is appropriate given the already-comprehensive 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: 'Find tools by describing the data or task.' It specifies the resources covered (SEC filings, financials, FDA drugs, etc.) and distinguishes itself from siblings by being a meta-tool for discovery, explicitly mentioning it returns ready-to-call tool schemas.

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

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

The description gives explicit when-to-use guidance: 'Use when you need to browse, search, look up, or discover what tools exist' and 'Call this FIRST when you have many tools available and want to see the option set.' It clearly positions this as the initial discovery step, differentiating it from direct tool invocation.

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 the annotations (readOnly, openWorld, idempotent), the description discloses parallel fan-out across sources, the USPTO PatentsView API sunset with soft-fail behavior, GDELT→GNews fallback, and LEI via GLEIF. This adds significant behavioral context not inferable from annotations alone.

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?

Long single paragraph but every sentence carries useful information, including examples, fallbacks, and return field details. Slightly dense and run-on, but nothing is wasted; the front-loaded examples help quickly match user intent.

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 complex tool with no output schema, the description lists all key return components (cik, company_name, recent_filings with URIs, fundamentals sorted by period_end, patents, news, LEI) and covers edge cases (patent soft-fail, name not supported). It is complete enough for an agent to invoke correctly and set expectations.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by reinforcing the ticker/CIK formats, explicitly mentioning zero-padded CIK, and cross-referencing resolve_entity for names. This goes beyond the schema's own 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 identifies the tool as a full cross-source profile for US public companies, with a specific verb ('profile', 'tell me about') and resource. It distinguishes itself from sibling tools like resolve_entity and single-source lookups by emphasizing parallel fan-out and holistic view.

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: 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view.' It also states the exclusion for names ('names not supported — use resolve_entity first'), making when-to-use and when-not-to-use crystal 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 declare destructiveHint=true and idempotentHint=true. The description adds value by specifying 'previously stored memory' and 'clear sensitive data', giving behavioral context about what the deletion affects. This goes beyond the annotations without contradicting them.

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

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

Two sentences, front-loaded with the core action, and every sentence contributes meaningful guidance. No redundant or verbose language.

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

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

Given the simple single-parameter tool with clear annotations and no output schema, the description fully covers purpose, usage timing, and relationship to sibling tools. 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?

Schema description coverage is 100% and the parameter 'key' is fully described as 'Memory key to delete'. The description mentions 'by key' but adds no additional detail beyond the schema, so a baseline score of 3 is appropriate.

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

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

The description clearly states 'Delete a previously stored memory by key', specifying the verb (delete), resource (memory), and scope (by key). It distinctly separates from siblings like remember and recall by indicating it removes data rather than storing or retrieving.

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, the task is done, or you want to clear sensitive data the agent saved earlier.' It also mentions pairing with remember and recall, providing context but without explicitly saying when not to use, so a 4 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 convey readOnly, idempotent, and non-destructive behavior. The description adds valuable context by detailing the internal steps: 'Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format.' It also clarifies the output is 'a single text blob ready to drop at site-root/llms.txt,' making the tool's behavior transparent 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?

The description is four sentences that efficiently front-load the main action and process. The 'Useful for' list adds practical value without fluff. Minor redundancy exists in describing output twice ('standard llms.txt markdown format' and 'single text blob'), but overall it is well-structured and concise.

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

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

With no output schema, the description compensates by explaining the output format and destination. Combined with full parameter schema coverage, helpful annotations, and clear use cases, the description provides enough context for correct invocation. It does not cover edge cases like network failures, but these are less critical for a read-only, idempotent tool.

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

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

The input schema covers both parameters fully: url as 'Full URL of the site to summarize' and max_links with default/max. The description hints at 'key links' which aligns with max_links, but it does not add meaningfully beyond the schema. With 100% schema coverage, the 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?

The description uses a specific verb and resource: 'Generate a production-ready llms.txt file for any URL.' It clearly distinguishes itself from siblings by focusing on generating the llms.txt file itself, not just scanning or researching. The mention of 'standard llms.txt markdown format' and site-root placement makes the purpose unambiguous.

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

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

The description provides clear use cases: 'getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.' However, it does not explicitly name alternative tools or state when not to use this tool, falling short of a 5.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description only needs to add behavioral context. It does so by specifying the exact output scope: current deals across stores, historical lows, and price trends. This goes beyond the annotations without contradicting them.

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

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

The description is a single, well-structured sentence that leads with the action and then provides detail after a colon. Every word serves a purpose, making it highly 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 one clearly documented parameter, comprehensive annotations, and existing output schema, the description is complete for an agent to understand what the tool does and when to invoke it. No additional explanation of return values is needed because the output schema covers that.

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

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

The input schema already has a full description for the single 'id' parameter (CheapShark game ID from search_games), achieving 100% schema coverage. The tool description adds no additional parameter-level meaning, so the baseline of 3 applies.

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

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

The description uses the specific verb 'Get' and clearly identifies the resource: complete pricing history for a game. It enumerates the three component data types (current deals, historical lows, price trends), distinguishing it from siblings like search_games (which finds game IDs) and search_deals (which searches deals).

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

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

The description implies usage by stating its purpose—retrieving comprehensive pricing for a single game—but does not explicitly exclude alternatives like search_deals. The schema description notes the ID is obtained from search_games, which hints at the appropriate flow, but an explicit when-to-use would be stronger.

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 non-destructive behavior. The description adds useful context beyond this: it identifies the scope ('tracked' retailers) and the return payload (store names and IDs). This is appropriate given the low bar for annotation coverage.

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

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

The description is two sentences, front-loaded with the action ('View all tracked game retailers'), and every word adds value—including examples and the return/usage explanation. 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?

For a zero-parameter, read-only tool with an output schema, the description fully covers what it does, what it returns, and why to use it. The output schema handles return structure details, so no further elaboration is needed.

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

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

The tool has 0 parameters, so parameter semantics are not a concern. The baseline for 0 parameters is 4, and the description does not need to explain any parameters since none exist.

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

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

The description clearly states the tool's function: 'View all tracked game retailers' with examples (Steam, Epic Games, GOG). It also specifies the return value (store names and IDs) and its use case (filtering deals), distinguishing it from game- or deal-related sibling tools.

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

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

The description implies usage context: 'for filtering deals by specific stores' tells the agent when to use this tool. It doesn't explicitly name alternatives, but no sibling tool lists stores, so it is implicitly the correct choice for retrieving store IDs.

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

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

With annotations already declaring readOnlyHint, destructiveHint, and idempotentHint, the description adds contextual behavior by listing the exact return fields (id, type, params, created_at, last_fired_at, fire_count) and scoping to the caller's subscriptions. This 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?

Two concise sentences with front-loaded action and zero wasted words. It efficiently covers purpose, return fields, and usage context.

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

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

Despite having no output schema, the description lists all expected return fields and explains typical use cases. With only one optional parameter and strong annotations, this fully covers what an agent needs to invoke and interpret results.

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

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

The schema already documents the single parameter include_inactive with 100% coverage. The description's mention of 'active subscriptions' aligns with the default false, but adds no significant new semantic detail 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 lists the caller's active subscriptions, using a specific verb and resource. It distinguishes itself from sibling tools like subscribe and unsubscribe by focusing on listing with return fields.

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: to review monitoring before adding more or to find an id to cancel. It does not explicitly mention when-not-to-use or name alternatives, but the context is distinct.

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

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

Despite neutral annotations, the description richly discloses behavior: it explains the claim_token flow, rate limiting ('Rate-limited to 5 per identifier per day'), cost ('Free; doesn't count against your tool-call quota'), and the internal review process ('The team reads digests daily'). It also cautions against pasting end-user prompts, adding behavioral nuance 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 front-loaded with the core purpose, then efficiently packs essential operational details like rate limits and claim_token behavior. Every sentence earns its place; the only minor issue is that it could be trimmed slightly, but it remains well-organized and readable.

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

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

Despite having no output schema and only neutral annotations, the description covers the full expected behavior: what the tool does, when to use it, what to avoid, what to expect upon filing (claim_token), how to follow up, and operational constraints (rate limit, free). This is complete for a feedback tool with nuanced usage rules.

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 baseline is 3, but the description adds meaningful semantic context beyond the schema, particularly for `claim_token`: 'Filing without an account returns a `claim_token`; pass it back later... to read whether it was fixed and what changed.' This explains the inter-parameter relationship and usage pattern, enriching the structured parameter descriptions.

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

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

The description opens with a specific verb+resource: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It clearly differentiates from siblings by explicitly stating 'ONLY for tools served by this Pipeworx connection' and contrasts with other MCP servers, making the tool's scope unmistakable.

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 states when to use each feedback type: 'Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise).' It also gives a clear exclusion: 'if the tool came from a different MCP server... file it with that server instead.'

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 the readOnly/idempotent annotations, the description discloses the data source ('CF analytics-engine'), privacy ('no PII, just (pack, tool, count)'), and caching behavior ('Cached 5min-1h depending on window'). This provides meaningful operational context for the agent 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 front-loaded with the core purpose, then organized into numbered use cases and a concise data/caching note. Every sentence contributes distinct useful information with no fluff or redundancy.

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

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

The description fully covers a simple read-only tool: what it returns, what the window controls, why it exists, how the data is sourced, and freshness/caching. No output schema is present, but the 'just (pack, tool, count)' statement gives a clear return shape.

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 complete (100%) with an enum and description of window semantics. The tool description adds that cache duration depends on the window, giving a parameter-dependent behavioral nuance not present in the schema. However, it largely repeats the window options already in the schema.

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

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

The description opens with a specific question ('What other AI agents are calling on Pipeworx right now') and explicitly states it returns top tools, top packs, and total call volume over a recent window. This clearly identifies the resource and differentiates it from sibling tools like discover_tools or search_within.

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 'Useful for' list provides concrete scenarios: discovering hot data sources, confirming canonical tools, and checking alignment with other agents' needs. It also explains window trade-offs ('shorter windows surface what's hot right now; longer windows show steady-state demand'), but does not explicitly name alternatives or when-not-to-use.

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

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

The description adds rich behavioral context far beyond the read-only/idempotent annotations. It explains the fill check with live CLOB depth, warns 'do not trade it' when realizable_edge_pp <= 0, describes the Jaccard similarity anchor (>=0.30), and details the partition filter dropping placeholder slugs >20%. This is exactly the kind of non-obvious behavior that annotations cannot 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 long, but it is well-structured with clear mode breakdowns and labeled sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK). Every sentence adds necessary detail, though a few points could be tightened. It is appropriately sized for the tool's complexity, but not as lean as a two-sentence description.

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

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

With no output schema present, the description carries the full burden of explaining return values, and it does so thoroughly: opportunities[] fields, partition_check fields, skipped_low_similarity, placeholders_filtered, and fill_check outcomes. It also covers edge cases (null signal, thin legs, realizable edge <= 0) and points to a sibling for further needs. This is complete for a tool of this complexity.

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

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

Even though schema coverage is 100% and each parameter already has a good description, the tool description goes much deeper. It gives concrete examples ('fed-decision-may-2026'), explains what each mode does internally (walks child markets, checks date-axis/threshold-axis ordering, runs comparator on union), and notes that full URLs are accepted. This far exceeds the schema's own 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 opens with a specific verb+resource: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It clearly distinguishes the tool's methods from siblings and immediately describes the three invocation modes (no args, event, topic). This is a model example of purpose clarity.

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

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

The description explicitly explains when to use each mode: 'Call with NO args for a trending_scan... pass `event` for the strongest per-event partition_check, or `topic` for a themed cross-event scan.' It also points to an alternative: 'For custom sizing use polymarket_fill_risk.' However, it does not explicitly exclude other sibling tools like polymarket_edges or polymarket_edge_tracker, which might also find arbitrage-related opportunities.

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 extensive behavior beyond annotations: caching ('Cached 1h at the KV level keyed on all knobs'), response segmentation (by_segment, fed_note, _diagnostics), model family details, parameter interactions, and the 24h-move warning. It also explains why Fed bets are excluded, adding significant 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 long and dense but well-structured with segments, parentheses, and front-loaded purpose. Each sentence provides substantive detail, though it is arguably over-specified for a quick read; still, it earns its place for the tool's complexity.

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

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

Given no output schema, the description fully details the response structure (by_segment, fed_note, _diagnostics), opportunity fields (edge_pp_net, kelly_fraction, liquidity, spread_pp), and filtering knobs. It leaves little ambiguity for an agent.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaningful context beyond the schema, e.g., min_partition_leg_kelly applies to per-leg Kelly inside top_legs because partition arbs return parent-level kelly=0, and explains slippage assumptions. This goes beyond the schema descriptions.

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

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

The description clearly states a specific verb ('Scan') and resource ('top Polymarket markets') plus the output ('opportunities where Pipeworx data disagrees with market price'). It distinguishes from siblings like polymarket_arbitrage and polymarket_edge_tracker by emphasizing multi-model edge discovery rather than pure arbitrage or tracking.

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

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

It identifies a clear use case: 'Built for "what should I bet on today"' and notes agents discover opportunities without paging hundreds of markets. It does not explicitly name alternatives or exclusions, so it stops short of a 5, but the context is strong.

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 the tool as readOnly and idempotent, but the description adds significant behavioral context: the structure of tracked[] and expired[] lists, the meaning of snapshot_gaps, the 60-day TTL limit, and that decay is computed on daily closes of edge_pp_net rather than intraday. This goes well 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?

The description is dense but well-structured: an opening question, a concise args block, a detailed RESPONSE breakdown, and a LIMITS section. Every sentence adds operational value, and the organization makes the information easy to parse despite 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?

With no output schema, the description fully specifies the response shape (tracked[] with edge time-series, trend, decay; expired[] with lifespan; snapshot_dates[]), and discloses TTL, snapshot-write behavior, and data limitations. It answers the key operational questions an agent would have when invoking the tool.

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

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

The input schema already provides 100% parameter coverage (days with default/clamp, window with enum/default). The description merely restates the default values and introduces the phrase 'snapshot family' which is vaguer than the schema's explicit enum. No substantial added meaning, so baseline 3 is appropriate.

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

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

The description clearly states the tool's purpose with a specific verb+resource: tracks edge persistence and decay from daily polymarket_edges snapshots. It directly answers the question 'how long has this edge existed and is it shrinking?' and differentiates from sibling tools by focusing on time-series behavior rather than point-in-time edge computation.

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 through the trading distinction between a 'fresh wide edge' and a '3-week-old wide edge', making the use case clear. However, it does not explicitly name alternative tools or state when not to use it, just below the threshold for a 5.

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

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description aligns with those. It adds extensive behavioral context: walks the order-book ladder, returns per-leg fill detail, identifies thin_legs, forced_directional_risk, and warns about partial-fill conversion to unhedged positions. This exceeds what annotations 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 long and dense, but it is front-loaded with core purpose and then separates single-market vs basket modes clearly. Every clause adds operational detail needed for correct invocation. It could be tightened, but complexity justifies the 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?

With no output schema, the description must explain return values, and it does comprehensively: verdict values, fields like top_of_book, vwap_fill_price, slippage_pp, shares_filled, theoretical_sum vs realizable_sum, capture_ratio, etc. It also covers prerequisites (market or event) and risk context. Nothing critical is missing.

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

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

Schema coverage is 100%, but the description adds rich semantics beyond the schema: size_usd interpretation changes by mode (max spend vs target proceeds vs settlement notional), side defaults, and default behavior in basket mode (auto from partition sum). This is far beyond baseline schema documentation.

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 begins with a specific verb+object: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes itself from siblings like polymarket_arbitrage (signal generation) and polymarket_edges (theoretical edges) by focusing on fill risk against live book depth.

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 guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains when basket mode is appropriate and warns about partial fill risks, making the when-to-use 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?

The description goes far beyond the annotations by explaining that the spread is only meaningful when bet shapes are equivalent, and it details safety fields like compatibility_warning, temporal_alignment, and skipped_cross_type/subtype. It transparently discloses the tool's limitations and when the output is not reliable, which is essential 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 (TWO MODES, RESPONSE, SAFETY FIELDS) and no filler. It earns its length by packing necessary details about output fields and compatibility logic, though it could be trimmed slightly without losing meaning.

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

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

Given the absence of an output schema, the description provides a comprehensive account of the response contents: leg-by-leg prices, spread with top_spreads_pp, compatibility_warning, temporal_alignment, and skipped pair counters. It also covers edge cases and limitations, making it fully sufficient for an agent to invoke and interpret the tool correctly.

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

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

Although the schema already describes all three parameters with 100% coverage, the description adds interaction semantics by explaining that topic selects a pre-mapped shortcut while kalshi_event_ticker and polymarket_event_slug explicitly override the mapped sides. This goes beyond the schema's individual field descriptions, giving a fuller understanding of how parameters work together.

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 'Cross-venue spread between Kalshi and Polymarket for the same resolving question,' which uses a specific resource (spread) and clearly distinguishes this tool from siblings such as polymarket_arbitrage. It further clarifies two operational modes and the nature of the returned data, leaving no ambiguity about what the tool does.

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 explains the two modes (topic shortcuts vs explicit pairings) and when to use each, and it warns that most pre-mapped topics return compatibility_warning and are not tradeable. It provides clear context but does not name alternative sibling tools as replacements, so it stops short of full when-to-use/not-use coverage.

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 the readOnlyHint and idempotentHint annotations, the description adds valuable behavioral context: scoping to the caller's identifier (anonymous IP, BYO key hash, or account ID). It also clarifies the dual behavior (retrieve vs. list all keys) in prose. 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 efficiently written in three sentences, with each sentence adding a distinct piece of information: purpose/function, use case, and scoping/related tools. No fluff or redundancy.

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

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

For a simple tool with one optional parameter, rich annotations, and no output schema, the description fully covers purpose, usage context, and data scoping. It is complete enough for an agent to decide when and how to invoke recall correctly.

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

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

The input schema already provides 100% parameter coverage, including the behavior for omitted keys. The description repeats this information without adding new meaning or syntax details beyond what the schema offers, so a baseline score of 3 is appropriate.

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

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

The description clearly states the tool retrieves a value previously saved via remember, with an optional list-all-keys mode. It distinguishes itself from siblings by explicitly mentioning remember and forget, and by scoping to storage-related context.

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 recall: 'Use to look up context the agent stored earlier' and 'without re-deriving it from scratch.' It also points to related tools (remember, forget) for complementary operations, but does not explicitly state when not to use it or name a distinct alternative.

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 readOnlyHint annotation by stating that setting mark_read:true will flag returned events read, modifying the persisted feed state. Since readOnlyHint indicates the tool does not produce side effects, this is a serious inconsistency, so the score is 1.

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 with no redundancy; front-loaded purpose, then return format, filtering, mark_read, and alternative access. Every sentence adds new information, making it appropriately sized and well-structured.

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

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

Covers return payload, filtering options, mark_read effect, polling behavior, and alternative endpoint. With 5 optional parameters and no output schema, this is sufficiently complete for an agent to invoke it correctly.

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

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

Schema covers all 5 parameters with descriptions, so the baseline is 3. The description adds an example for type ('sec_8k'), explains the consequence of mark_read on future calls, and clarifies the 'since' filter, providing 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 'Pull fired events from your subscription feed', which clearly specifies the verb and resource. It distinguishes from siblings like 'recent_changes' by focusing on subscription feed alerts and details the return payload, making its purpose unambiguous.

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

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

It states 'Polls work fine' and notes an HTTP endpoint for scripts/dashboards, implying when to use the tool vs alternatives. However, it does not explicitly name sibling tools or exclusions, so it lacks explicit when-not-to-use guidance.

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

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

Beyond the read-only/idempotent annotations, the description reveals source-specific quirks (GDELT→GNews fallback on rate limits, USPTO soft-fail due to API sunset), the single-parallel-call nature, and the exact output structure (changes[] grouped by source, total_changes, pipeworx:// URIs). This is 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 dense and informative, front-loading the core purpose and query examples. While the enumeration of phrasings is somewhat repetitive, each part contributes to LLM understanding. It could be more structured, but everything 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?

With no output schema, the description still details the return structure (changes[] grouped by source, total_changes count, citation URIs) and covers edge cases (fallbacks, soft-fail). For a tool with multiple data sources and parsing quirks, this is highly 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%, so baseline is 3. The description adds practical guidance on the `since` parameter (ISO date or relative shorthand like '7d', '30d', '3m', '1y') and suggests '30d' or '1m' for typical monitoring. This goes beyond the schema's property 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 explicitly identifies the tool as a change feed for a company over a time window, listing concrete data sources (SEC EDGAR, GDELT/GNews, USPTO) and giving natural-language examples. It also distinguishes itself from entity_profile, making its unique role 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?

Provides explicit when-to-use guidance: 'Use entity_profile instead when you want the static profile... regardless of window.' It also includes exemplary queries and explains fallback behavior (GDELT→GNews) and the USPTO soft-fail, helping an agent decide when to invoke this tool.

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

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

Beyond annotations, the description discloses key-value scoping by identifier, persistent memory for authenticated users, and 24-hour retention for anonymous sessions. These details enrich the annotation hints without contradicting them.

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 core purpose, followed by usage context and storage details. Every sentence adds value with no redundancy.

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

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

Covers purpose, usage scenarios, storage semantics, and sibling relationships. Missing return-value information, but for a simple write operation with no output schema, the description is sufficiently complete.

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

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

Schema coverage is 100%, so baseline is 3. The description adds contextual examples (resolved ticker, target address, user preference) that illustrate how to populate key/value pairs, providing 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's function: 'Save data the agent will need to reuse later' with specific examples of what to store. It distinguishes from sibling tools by explicitly 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?

Provides explicit use cases ('Use when you discover something worth carrying forward') and names companion tools (recall/forget) as alternatives, but does not explicitly state when not to use this tool.

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

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

The description goes well beyond the annotations (which already declare readOnlyHint, idempotentHint, destructiveHint). It discloses internal cascading through multiple endpoints, graceful degradation (LEI/FIGI fallback when services are unavailable), and the output structure (unresolved identifiers listed explicitly under `unresolved`). These behavioral details are critical for the agent to understand outcomes and error states, and they do 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 well-structured: example queries first, then core purpose, then detailed supported types with paragraphs. It is longer than average but every sentence adds value (e.g., degradation behavior, unresolved handling, replacement of 2-3 lookups). Minor redundancy exists (the list of example queries could be shorter), but overall it is efficiently front-loaded with the main usage directive.

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 compensates by explaining return value structure: identifiers labelled by source, unresolved items explicitly listed, RxCUI + ingredient + brand for drugs. It also covers edge cases like graceful degradation and multi-source cascading. No gaps remain for the agent to infer; it knows exactly what to expect and how the tool behaves under failures.

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?

Even though the input schema describes both parameters with 100% coverage, the tool description adds substantial meaning: for the 'company' type it explains cross-source resolution (CIK, ticker, LEI, FIGI) and the ability to accept ticker, CIK, ISIN, or name, including how ISINs resolve to legal entities via GLEIF. For 'drug' it details RxCUI + ingredient + brand + citation. This rich context helps the agent understand what inputs are accepted and how they are processed.

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 concrete example queries ('What's the ticker for...') and states its core function: 'resolve a user-spoken NAME to the canonical/official identifiers other tools require as input.' It explicitly says 'Use FIRST whenever you have a name but need an ID,' which clearly distinguishes it from siblings like entity_profile or compare_entities. The verb (resolve) and resource (names to identifiers) 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 gives a strong usage directive: 'Use FIRST whenever you have a name but need an ID.' This tells the agent when to invoke this tool. However, it does not explicitly list when NOT to use it or offer direct comparisons to alternatives like entity_profile or compare_entities. The context is clear enough for an informed agent, but explicit exclusionary conditions are absent.

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 goes beyond the annotations by explaining the internal process: it delegates to ai_visibility_check per entity, ranks by score, and surfaces which entity is most/least recognized. It also discloses output structure (ranked list with score, confidence, signal density). No contradiction with the readOnlyHint and idempotentHint 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, front-loaded with the purpose, followed by method, use case, and return value. Every sentence earns its place—no fluff or repetition of schema or annotation content.

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

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

Despite lacking an output schema, the description specifies the return format (ranked list with score, confidence, signal density). It also names the underlying tool (ai_visibility_check) and mentions the optional context parameter's purpose, making the tool's behavior fully comprehensible for an agent.

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

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

Schema coverage is 100% with clear descriptions for all four parameters. The description adds only a slight semantic overlays (e.g., treating the first entity as 'your brand' and others as competitors), but that is already encoded in the schema ('First entry treated as the "subject"'). Thus description does not add significant parameter 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 opens with a specific verb+resource: 'Compare AI visibility across multiple entities side-by-side.' It clearly distinguishes from siblings like ai_visibility_check (single-entity) and compare_entities (generic comparison) by focusing on AI visibility and multi-entity ranking.

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 context for competitive AI-marketing audits and an example question. It mentions probing each entity with ai_visibility_check, implying this is the multi-entity version of that tool, but it does not explicitly state when not to use it (e.g., 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 the readOnly/idempotent annotations, the description discloses partial failure handling (bundlephobia first measurement 5-30s, sources_failed listing timeouts), the exact output structure (summary fields, per-advisory detail, links, alternatives), and the NPM v1 restriction. This significantly enriches 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 front-loaded with a clear purpose, then efficiently packs usage, ecosystem scope, output fields, and failure behavior into three dense sentences with no filler. Every clause 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 complex composite tool with no output schema, the description covers the return values (summary block list), timing, failure degradation, and scope. Sibling tools and annotations fill the remaining context, making this sufficient for an agent to call 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 already describes both parameters with 100% coverage (package accepts scoped names, version defaults to latest). The description does not add syntax or format details beyond the schema, so the 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 opens with a specific composite check verb 'should I add this npm package' and explicitly names the two services it fans out across (deps.dev, bundlephobia), distinguishing it from sibling tools. It clearly identifies the tool as a one-call advisory for npm packages.

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

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

Explicitly instructs when to use: whenever an agent asks 'is X safe/popular/small' or 'what does adding lodash cost me', and states the alternative for other ecosystems ('PyPI/Maven/Cargo/Go fall under deps.dev:version directly'). This gives clear invocation context and exclusion.

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. The description adds value by specifying that results are limited to 'active' deals and by listing the exact fields returned, which is useful behavioral context 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?

The description is two sentences long, front-loaded with the core purpose, and every clause adds information. It is efficiently written with no redundant phrases.

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 good annotations, full schema coverage, and presence of an output schema, the description is largely complete. It covers the core functionality and return values. The only minor gap is the inconsistency about the 'platform' filter, which could confuse agents, and no explicit note about pagination defaults, though the schema covers page_size.

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

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

The input schema has 100% coverage with each parameter described, so the schema carries the heavy lifting. The description adds only a summarized list of filter types (store, platform, discount level), but interestingly 'platform' is not a parameter in the schema, which is a slight inconsistency. Overall, the description does not significantly enhance what the schema already provides.

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

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

The description clearly states the tool 'Search active game deals' with optional filters, which is a specific verb+resource. It distinguishes itself from sibling tools like search_games by focusing on deals, and the returns list (title, store, price, savings, scores) makes the purpose unambiguous.

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

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

The description implies usage: it is for searching active game deals, which is clear context. However, it does not explicitly mention alternatives or exclusion criteria (e.g., 'use search_games for general game info'), leaving the comparison to siblings to be inferred.

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, and non-destructive behavior. The description adds transparency by specifying the return values (cheapest price, deal ID, availability info) and the cross-store scope, which is not covered 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, concise sentence that front-loads the primary purpose and includes key return information. Every word adds value with no redundancy.

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

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

For a simple search tool with two parameters and an output schema, the description covers the main purpose and return details. It lacks explicit alternative usage or special behaviors, but the schema and annotations fill most 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 the parameters are fully documented in the schema. The description adds no additional meaning beyond confirming that 'query' is a game title; 'limit' is not mentioned, but its meaning is already clear from 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 ('Find'), the resource ('games by title'), and the purpose ('compare current prices across stores'). It distinguishes itself from siblings like search_deals and get_game_details by focusing on title-based search for price comparison.

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

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

The description implies when to use the tool (when you need to find games and compare prices), but it does not explicitly mention when not to use it or provide alternatives. No direct references to sibling tools or exclusionary guidance.

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

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

The description discloses technical behaviors beyond the readOnly/idempotent annotations: the embedding model (BGE-base-en), similarity method (cosine), window size (500-char overlapping), limit (200K chars, truncated and flagged), and the return of character offsets for verification. These details add meaningful operational context that annotations don't cover.

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, front-loading the core purpose before moving to usage guidance and technical details. Every sentence earns its place; there is no padding or repetition of schema 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?

With no output schema, the description compensates by specifying exactly what is returned (top-N passages, character offsets, similarity scores) and how edge cases are handled (truncation with flag). It also places the tool in a broader workflow, making it fully self-contained for an agent.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds value by giving concrete examples for 'text' (SEC 10-K body, article) and 'query' ('supply-chain risk', 'drug interactions with warfarin'), and by explaining the 'limit' behavior as returning top-N passages. These enrich the bare schema definitions, though not exhaustively.

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 'Semantic search INSIDE a fetched record,' which states a specific verb and resource, clearly distinguishing this tool from siblings like ask_pipeworx. It further clarifies the tool returns passages with offsets and scores, not a whole-answer generation, making the purpose unmistakable.

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 name-drops the alternative workflow: 'Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document.' This provides both when-to-use and when-to-consider-another-tool 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?

The description adds behavioral context beyond annotations: accounts that cannot persist subscriptions, the always-on feed, sms verification and per-day cap, and the webhook auto-disable (in the schema). No contradiction with readOnlyHint=false or idempotentHint=true.

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 around types and delivery channels. Every sentence carries information, though it is longer than strictly necessary. It front-loads the primary purpose.

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

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

The description covers core aspects: action, return value, auth requirement, type-specific examples, and delivery options. It lacks an explicit pointer to sibling management tools and does not describe the output schema (none exists), but for a subscription-creation tool with a rich schema, it is sufficiently complete.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds concrete examples for sec_8k, polymarket_edge, and fred_series, and clarifies the delivery structure. It does not cover all types in the description, but the schema handles those.

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

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

The description states a clear action ('Create a proactive monitoring subscription') with a specific resource ('live-data event stream') and explains the return value. It distinguishes itself from sibling tools (e.g., list_subscriptions, unsubscribe) by focusing on creation.

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 clear context: requires a Pipeworx OAuth account, explicitly lists supported subscription types, and explains delivery channels. It does not explicitly mention alternatives like list_subscriptions or unsubscribe, but the context is sufficient for an agent to understand when to use this tool.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds behavioral context by explaining the output format (category-bucketed examples with exact tool+argument shapes from the live catalog) and the optional `topic` filter, which is useful beyond what annotations 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?

While longer than typical descriptions, every sentence earns its place: it lists example queries, enumerates categories, explains the tool+argument mapping, and gives usage guidance. The structure is front-loaded with the most common phrases, making it scannable and information-dense.

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

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

With no output schema and a single optional parameter, the description fully covers what the tool returns (category-bucketed examples with tool+argument shapes), how to focus via `topic`, and when it should be called first. It also mentions the source (live catalog of tools), leaving no critical gaps 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?

Schema coverage is 100%, so the baseline is 3. The description goes beyond the schema by explaining the effect of passing `topic` (e.g., 'finance', 'pharma', 'betting') to focus and omitting it for a full spread. This practical guidance adds meaning to the parameter 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 uses a specific verb ('returns') and resource ('category-bucketed example questions') while also detailing that each example includes the exact tool and argument shape. It clearly differentiates from sibling tools like ask_pipeworx or discover_tools by positioning itself as the onboarding entry point for 'what can I ask'.

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

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

Explicitly states 'Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools.' This provides clear when-to-use guidance and names the meta-tools (ask_pipeworx, entity_profile, compare_entities) as the next steps, covering both usage and 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?

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true), the description discloses ownership enforcement, row deactivation rather than deletion, and preservation of historical events via recent_alerts. These are meaningful behavioral traits that assist an agent in predicting side effects.

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

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

The description is two sentences, front-loaded with the core action, and every sentence adds value: the first states the operation, the second covers ownership, soft-delete, and downstream impact. There is no fluff or redundancy.

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

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

For a single-parameter mutation tool with no output schema, the description explains what happens (cancellation), constraints (ownership), side effects (deactivation not deletion), and related context (recent_alerts). Combined with the annotations, it gives an agent enough to invoke correctly and set expectations.

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 for the single 'id' parameter is 100%, and the schema already describes it as a UUID returned by subscribe. The description adds minimal parameter-specific meaning beyond restating 'by id,' so it does not exceed the baseline expected when the schema is complete.

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 ('Cancel') and resource ('subscription by id'), clearly distinguishing it from sibling tools like 'subscribe' and 'list_subscriptions.' It also states the intended effect (deactivation) and how it differs from deletion, making the purpose unmistakable.

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: use this tool when you need to cancel a subscription by id. It notes ownership enforcement and the soft-delete behavior, which implies usage constraints, but it does not explicitly contrast with alternatives or state when not to use it. The context is clear enough without 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 read-only, open-world, idempotent, and non-destructive. The description adds crucial behavioral context beyond annotations: the exact verdict vocabulary, the meaning of 'could_not_verify' (never evidence) with verification_error details, and the meaning of 'unsupported' (no source covered). It also explains the fallback pipeline, giving agents a clear mental model of what happens. 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 longer than average but earns every sentence: it front-loads with natural-language trigger phrases, then explains the two routing paths, the return value, and a critical caller caveat. The 'IMPORTANT for callers' section is well-structured and the text is free of redundancy.

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

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

For a tool with no output schema and moderate complexity, the description covers all essential aspects: input examples, routing logic, return values (verdict, value with citation, reasoning), error semantics, and the fact that it replaces multiple sequential calls. It is sufficiently complete for an agent to invoke correctly and interpret results.

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

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

Schema coverage is 100% and both parameters ('claim', 'tolerance_pct') are well-described in the schema already. The description mostly restates the same information (e.g., tolerance override, default implied by wording). It does not add significant new semantic value beyond what the input schema provides, so the 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?

The description uses specific action verbs and examples ('fact check', 'verify the claim that…') to clearly state this tool performs natural-language claim verification against authoritative sources. It distinguishes itself from sibling search/research tools by explicitly noting it replaces 4–6 sequential calls and by describing the structured SEC EDGAR fast path for financial claims.

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 states when to use: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also differentiates the two routing paths (company-financial vs. any other claim). However, it does not explicitly name alternative tools or state when not to use it, though the 'Replaces 4–6 sequential calls' hint implies a comparison. Slight gap in exclusions/alternatives.

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