Carbon Interface

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

Description adds substantial context beyond annotations: default model is free, Anthropic requires a BYO key and incurs cost, output structure includes per-model and combined view. Annotations already declare readOnlyHint, idempotentHint, and non-destructive nature, so no contradiction.

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

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

Description is efficient: four sentences covering action, defaults, returns, and use cases. No redundant phrases, though it could be slightly more compact without losing meaning.

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

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

Given no output schema, description adequately describes the return format. Parameters are fully explained, and the tool's purpose is well-covered. Could mention that only one entity is probed per call, but overall complete for a tool of this complexity.

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

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

Schema coverage is 100%, but description enriches by clarifying that 'workers-ai' is the default model, '_apiKey' is only needed for Anthropic and passed through directly, and 'context' helps disambiguate entities. This adds practical guidance 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?

Description specifies a clear verb-resource pair ('probe LLMs about entity') and a measurable outcome ('score visibility 0-100'). It distinguishes from sibling tools by focusing on AI visibility/brand presence across multiple models, unlike general research or entity profile 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?

Description explicitly states use cases ('AI-marketing audits, pre-launch brand checks, competitive monitoring') and hints at when to use (e.g., probing multiple models). However, it does not explicitly tell the agent when not to use it or compare directly to sibling tools like scan_competitor_ai_presence.

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, destructiveHint. Description adds context about routing mechanism (5,008 tools, 1318 sources) and return format (structured answer with citation URIs). No contradiction. Lacks specific error handling or rate limits, but the annotations cover the safety profile sufficiently.

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

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

The description is relatively long but well-structured: starts with a strong recommendation, then describes capabilities, usage guidelines, examples, and step-up options. Could be slightly more concise, but the structure earns a 4.

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 (5,008 tools, 1318 sources), the description is remarkably complete. It explains routing, data coverage, citation mechanism, and when to use alternatives. No output schema exists, but the description adequately states the return type.

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

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

Schema coverage is 100% with all aliases documented. Description reinforces that 'question' accepts natural language and provides examples, but doesn't add new meaning beyond schema. Baseline 3 is appropriate.

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

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

The description clearly states the tool routes questions to over 5000 tools and sources for authoritative structured data with citations. It specifies the verb 'ask' and resource 'Pipeworx', and distinguishes from siblings like ask_pipeworx_grounded and deep_research by defining scope and use cases.

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

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

Provides explicit guidance: 'PREFER OVER WEB SEARCH', lists many example queries, and clearly states when to use alternatives (grounded for hallucination-resistance, deep_research for broad questions). Also notes that breaking news is handled here. This is comprehensive and actionable.

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

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral context: it is a live experimental router with source-preference ranking, and it falls back to nothing (it is a full working router). 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 concise and front-loaded with the purpose and key difference. It efficiently communicates the experimental nature and fallback behavior. A minor redundancy could be trimmed, but overall well-structured.

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

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

Given the rich annotations and lack of output schema, the description adequately explains the tool's experimental status, routing behavior, and fallback. It mentions the same response shape as ask_pipeworx, which is sufficient for context.

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

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

Schema coverage is 100%, so the schema already documents all parameters (question and its aliases). The description does not add new parameter meaning beyond stating that it accepts the same arguments as ask_pipeworx, which is consistent. Baseline 3 is appropriate.

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

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

The description clearly states it is a beta version of ask_pipeworx, an identical universal router with the same set of 5,008 tools and arguments, but with experimental source-preference ranking. It distinguishes from the stable version by noting the 'candidate routing improvements' and 'experimental edge'.

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 to use it exactly like ask_pipeworx when you want the newest routing. It explains when to choose this over the stable router and highlights the source-preference ranking feature. Also mentions results are compared against the stable router.

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 it as read-only, open-world, idempotent, non-destructive. The description adds key behavioral traits: hallucination resistance, answer extraction only from tool result, explicit refusal reasons, and cost impact. 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?

Description is information-dense and front-loaded with purpose. However, it could be structured into multiple sentences for readability. All content is relevant and earns its place.

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

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

Given the tool's complexity (tool routing, extraction, refusal reasons) and lack of output schema, the description thoroughly covers return format, potential refusal reasons, and behavior differences. It leaves no significant 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% with descriptions for each alias. The description only adds 'Your question in natural language' and lists aliases, which adds minimal semantic value beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states it is a 'hallucination-resistant answer mode for high-stakes reads' and details the process of tool routing and answer extraction. It distinguishes itself from the sibling 'ask_pipeworx' by specifying a different use case (quoted/cited vs casual lookups).

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

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

Explicitly states when to use: 'whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts'. Also provides when-not-to-use: 'prefer ask_pipeworx for casual lookups', and mentions the trade-off of an extra LLM call.

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

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

Beyond annotations (readOnly, idempotent, non-destructive), the description discloses many behaviors: low-confidence short-circuit, closed market handling, wide-spread indicator, resolver contract, and resolution-rule risk. It also explains the parent_event extractor and news fallback mechanisms. 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 long but well-structured with clear section headers (CLASSIFIERS, FAN-OUT EXAMPLES, RESPONSE SHAPES, etc.), making it scannable. Every sentence adds necessary detail for a complex tool, though some redundancy exists (e.g., repeating input formats). Could tighten, but effective overall.

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

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

Despite lacking an output schema, the description thoroughly documents all key aspects: return fields (market, analysis, evidence), resolver contract, parent_event extractor, news fallback fields, safety mechanisms, and resolution-rule risk. It covers edge cases and provides complete context for using the tool effectively.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds value by elaborating on the market parameter's input formats (slug, URL, question text) and explaining depth and include_raw defaults and recommendations. This extra context justifies a 4.

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

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

The description clearly states the verb ('Research') and resource ('a Polymarket bet'), and explains the core functionality: pulling Pipeworx data, resolving, classifying, fanning out, and returning evidence. It distinguishes itself from sibling tools like polymarket_arbitrage by focusing on single-bet research.

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

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

The description explicitly lists use cases ('should I bet on X', 'what does the data say about Y', 'is there edge in Z') and provides examples of fan-outs for different bet types. It also explains when the tool will block or return limited data (low confidence, closed markets, wide spreads), giving clear guidance on when it is appropriate to use.

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

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

Annotations declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds context: pulls latest 10-K data from SEC EDGAR/XBRL with off-calendar fiscal year handling, FAERS counts, FDA approvals, trial counts for drugs. Results sorted by primary metric, returns paired data with citation URIs. No contradictions.

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

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

The description is compact yet rich, front-loaded with common query patterns. Every sentence adds value, covering examples, data sources, sorting, and output. It efficiently conveys all necessary information without repetition.

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

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

Given no output schema, the description explains the response contains paired data and citation URIs per entity, sorted by primary metric. It also notes off-calendar fiscal year handling and that the tool replaces 8-15 sequential lookups, providing full context.

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

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

Schema coverage is 100%. The description adds meaning: type specifies data sources and behavior, values format (tickers/CIKs for company, names for drug), min/max items. It clarifies that for 'largest'/'most', results are sorted so the top entity answers the query.

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

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

The description clearly states the tool does side-by-side comparison of 2-5 companies or drugs in one parallel call. It specifies the verb 'compare' and the resources, with examples like 'Compare X and Y', 'X vs Y'. It distinguishes from siblings by explicitly recommending preference over sequential lookups.

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

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

The description provides explicit when-to-use examples and instructs 'ALWAYS PREFER over sequential single-pack lookups'. It covers common query patterns and implies when not to use (single entity), aligning with sibling tool 'entity_profile'.

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

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

Beyond annotations (readOnly, openWorld, idempotent, not destructive), description adds rich behavioral details: returns evidence with confidence, source, fetched_at, citation, gaps, contradictions, hop field, semantic excerpting, expected time ranges, and iteration behavior. 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 lengthy but well-structured: starts with critical account warning, then core functionality, use cases, depth options, and output details. Every sentence adds value given tool complexity, though could be slightly more concise.

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

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

Despite no output schema, the description thoroughly explains the return findings packet with evidence, confidence, source, citation, gaps, contradictions, hop field, and timing. Covers all necessary context for a 2-parameter tool with complex behavior.

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

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

Adds meaning beyond schema: explains depth enum values with facet counts and iteration behavior (quick=3, standard=5 with gap recovery+contradictions, thorough=8 with leads+contradictions). For question, clarifies broad/multi-part is intended. Schema coverage is 100% but description enhances understanding.

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

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

The description clearly states the tool performs grounded multi-source research across 1318 structured data sources, decomposes questions, and returns a findings packet. It explicitly distinguishes from sibling tools like ask_pipeworx for single lookups or breaking news.

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 (broad/multi-part questions over structured data) and when-not-to (single lookups or breaking news, directing to ask_pipeworx). Also notes account requirements and depth level behaviors.

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

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

Beyond annotations (readOnly, idempotent), the description adds that results are 'ready to call directly, no second schema lookup needed', which explains the return format and behavioral trait. No contradictions.

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

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

Well-structured and front-loaded with purpose, but the long list of domains could be slightly trimmed. Still, each sentence adds value and the flow is logical.

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

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

Without an output schema, the description thoroughly explains what is returned (names, descriptions, schemas with examples) and when to use it, making it fully actionable 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 description coverage is 100%, so baseline is 3. The description does not add extra semantics beyond what the schema already provides for parameters; it merely repeats aliases.

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 finds tools by describing data or task, lists many specific domains, and positions it distinctly from sibling tools (e.g., bet_research, deep_research) by emphasizing discovery of the tool set.

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 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This gives clear when-to-use and when-not-to-use guidance, making it easy for an agent to decide.

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

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

Annotations already indicate read-only, idempotent, non-destructive. Description adds behavioral details: parallel call, fans across multiple sources, soft-fails for patents, specific return fields with URIs. No contradiction.

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

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

Description is dense with information and front-loaded with examples. Every sentence adds value, but length could be slightly trimmed without losing clarity. Still effective.

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

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

Given no output schema, description thoroughly explains return values: cik, company_name, recent_filings with URIs, fundamentals with sorting, patents, news, LEI. Covers edge cases like soft-fail for patents. Complete for the tool's complexity.

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

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

Schema coverage is 100%, but description adds meaning beyond schema: type is only 'company', value can be ticker or zero-padded CIK, names not supported. Provides example inputs like 'AAPL' or '0000320193'.

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

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

Description clearly states the tool provides a 'full cross-source profile of a US public company in ONE parallel call' with specific verb 'profile'. It distinguishes from siblings like 'resolve_entity' and 'compare_entities' by emphasizing holistic view and preference over chaining.

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 'ALWAYS PREFER over chaining single-pack lookups' when user wants a holistic view. Provides when-not: if only a name, use resolve_entity first. Also mentions input format restrictions (ticker or CIK).

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 openWorldHint. The description adds that the tool returns emissions in multiple units but does not disclose additional behavioral traits beyond what annotations provide.

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

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

The description is two sentences plus an example, efficiently conveying purpose and usage. Every part earns its place without redundancy.

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

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

The description covers purpose and gives an example, but lacks usage guidelines and does not fully address the tool's complexity given 5 parameters and an output schema. It is adequate but could be more complete.

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

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

Schema description coverage is 100%, so the baseline is 3. The description provides an example call but does not add significant semantic meaning beyond what the schema already documents.

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 estimates CO2 emissions from electricity usage and specifies output units. It is distinct from sibling tools like estimate_flight and estimate_vehicle by focusing on electricity.

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

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

The description provides no guidance on when to use this tool vs alternatives. It lacks context about selection criteria, prerequisites, or 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 indicate read-only, idempotent, non-destructive behavior. The description adds that it returns per-passenger and total emissions, but this is partially covered by the output schema. No contradictions.

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

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

The description is concise: two sentences and an example, front-loaded with the main purpose. Every sentence adds value without redundancy.

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

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

Given the tool's simplicity (3 params), annotations, and output schema, the description is complete. It covers purpose, inputs, example, and return values adequately.

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

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

Schema coverage is 100%, so baseline is 3. The description repeats what the schema provides but adds an example. No additional semantic depth 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 estimates CO2 emissions from a flight, using specific verbs and resource. It distinguishes from sibling tools like estimate_electricity and estimate_vehicle by focusing on flights.

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

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

The description implies usage for flight emissions but does not explicitly provide when to use or when not to use, nor does it mention alternatives. It lacks guidance on when to choose this tool over siblings.

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

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

Annotations already declare readOnlyHint, idempotentHint, etc. Description adds return units (grams, kg, metric tons) and references the Carbon Interface API, enhancing transparency without contradiction.

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

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

Two sentences plus an example; every sentence is informative and none are wasted. Front-loaded with purpose.

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

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

Given output schema exists, description need not detail returns, yet it still mentions return units. Complete enough for an agent to understand usage.

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

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

Schema covers all 4 parameters fully, but the description adds context via example showing unit usage and explaining the vehicle model ID comes from Carbon Interface, which adds meaning beyond schema.

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

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

Clearly states it estimates CO2 emissions from driving a vehicle with a specific verb and resource. Distinguishes from siblings like estimate_electricity and estimate_flight by focusing on vehicles.

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 inputs (distance, vehicle model ID) and an example, but does not explicitly contrast with sibling tools or state when to use this tool instead of alternatives.

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

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so description aligns. However, it does not disclose behavior when key does not exist (error vs. silent noop), which is a gap beyond what annotations provide.

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

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

Extremely concise: two sentences, no wasted words. First sentence delivers core action, second provides usage guidance.

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 delete-by-key tool with complete schema and good annotations, the description covers purpose and usage well. Lacks mention of return behavior (e.g., success/failure response), which is a minor gap given no 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%, and the description adds only context about purpose (previously stored memory) but no additional meaning about the key parameter beyond the schema's description.

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

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

The description clearly states the tool deletes a memory by key, using a specific verb and resource. It distinguishes from siblings by mentioning pairing with remember and recall.

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 (stale context, task done, clearing sensitive data) and pairs with related tools. Lacks explicit mention of when not to use, but guidance is clear given the context.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, establishing safety. The description adds that it fetches and extracts content, but does not disclose edge cases (e.g., handling of invalid URLs, size limits). Given annotation coverage, a 3 is appropriate.

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

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

The description is two sentences plus a bullet list of use cases, efficient and front-loaded. Every sentence adds value; no filler.

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

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

With 2 parameters, no output schema, and strong annotations, the description adequately explains the output format (single text blob) and typical use scenarios. Could mention response type explicitly, but overall 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% (both parameters described). The description does not add meaning beyond what the schema provides for url and max_links, aside from reiterating default and max. Baseline of 3 is correct.

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 'Generate' and resource 'llms.txt file', clearly stating it fetches a page and produces standard markdown. It distinguishes from siblings by specifying the output format and use cases (client indexing, own project, competitor audit).

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

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

The description explicitly lists three concrete use cases: getting a client's site indexed, drafting for own project, and auditing competitors. This provides clear guidance on when to use this tool vs alternatives.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description's additional details about returned fields and optional parameter add value without contradiction.

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

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

Two concise, front-loaded sentences with no wasted words. Every sentence adds value.

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

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

Given the tool's simplicity (one optional parameter, no output schema), the description fully covers purpose, return fields, and usage context. Annotations provide safety guarantees.

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 one boolean parameter described. The description does not add further meaning beyond the schema, justifying a baseline 3.

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

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

The description clearly states the tool lists the caller's active subscriptions and enumerates the returned fields. It distinguishes itself from sibling tools like subscribe and unsubscribe.

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 suggests use cases: reviewing subscriptions before adding more or finding an ID to cancel. It lacks explicit exclusions but provides sufficient context.

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

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

Discloses rate limit (5 per identifier per day), free usage, and no quota impact. Annotations have no contradictions; description adds behavioral context beyond annotations.

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

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

Five sentences, each adding value. Front-loaded with purpose, followed by usage guidelines, constraints, and rate limit. No unnecessary words.

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

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

Given 100% parameter schema coverage and no output schema needed, description fully covers all necessary context for tool use.

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

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

Schema coverage is 100%, but description adds meaning: explains type enum values, indicates context is optional, and provides message length guidance. Goes beyond schema.

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

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

The description clearly states the tool sends feedback to the Pipeworx team about bugs, missing features, or praise, using specific verbs and resource. It distinguishes from all sibling tools, none of which handle feedback.

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 specifies when to use (bug, feature/data_gap, praise) and what not to do (don't paste end-user prompt). Provides context on team read frequency and rate limit.

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

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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint. The description adds behavioral details: derived from CF analytics-engine, no PII, cached 5min-1h depending on window. No contradictions. Could also mention idempotency, but annotations suffice.

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

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

The description is two sentences plus a bullet list. The first sentence front-loads the core purpose. Every sentence adds value: returns, use cases, data source, caching. No redundant words.

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

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

Given the simple schema (1 optional param, no output schema), the description is complete. It explains return structure, data source, privacy, caching, and use cases. No output schema needed as the description clarifies the return fields.

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

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

Schema description coverage is 100% and the description adds value by explaining the window semantics: 'Shorter windows surface what's hot right now; longer windows show steady-state demand.' This complements the schema enum.

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 and resource: 'Returns the top tools, top packs, and total call volume over a recent window.' It distinguishes from siblings like 'discover_tools' (which lists all tools) and 'ask_pipeworx' (which queries). The name 'Pipeworx Trending' is self-explanatory.

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

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

The description explicitly lists three use cases: discovering hot data sources, confirming canonical tools, and aligning with agent needs. It also mentions caching. However, it does not explicitly state when not to use this tool or compare to alternatives like 'discover_tools'.

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

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

The description discloses key behavioral traits beyond annotations: default trending scan behavior, partition filter dropping placeholder slugs, FILL CHECK indicating when not to trade (realizable_edge_pp <= 0), and semantic anchor Jaccard similarity. Annotations already mark it as read-only, idempotent, non-destructive, and the description adds critical safety and execution details without contradiction.

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

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

The description is well-structured with labeled sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK) and front-loads core purpose and usage. While dense, every sentence adds value, though slightly longer than ideal; still maintains 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?

Without an output schema, the description thoroughly explains the response structure: opportunities[] with fields (gap_pp, suggested_trade, reasoning), partition_check details in event mode, and fill check conditions. It also references a sibling tool for custom sizing, making it self-contained for complex arbitrage logic.

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

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

Schema coverage is 100% with both parameters described. The description adds significant semantics: explains event mode accepts slugs/URLs and walks child markets, and topic mode cross-scans related events with examples. It also details internal logic like partition checks and fill risk, far exceeding schema descriptions.

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

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

The description clearly states the tool's purpose: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It differentiates between the default trending_scan, event mode, and topic mode, distinguishing it from sibling tools like polymarket_edges and polymarket_fill_risk.

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

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

The description provides explicit usage guidelines: '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 recommends event mode for specific markets and directs to polymarket_fill_risk for custom sizing, offering clear when-to and when-not-to guidance.

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

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

Annotations indicate readOnlyHint, openWorldHint, idempotentHint are true, and destructiveHint is false. The description adds significant behavioral context: cache behavior (1h at KV level), detailed model families with formula references, edge calculation details, and diagnostics for empty segments. This transparency exceeds what annotations alone provide.

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

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

The description is verbose, spanning multiple paragraphs with detailed model family expositions. While it is front-loaded with the main purpose and uses parentheses for structuring, it could be more concise. The length may deter quick comprehension.

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

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

Given the complexity (9 parameters, 3 segments with distinct logic, diagnostics, caching), the description is thorough. It explains the response structure, edge calculations, filtering knobs, and cache behavior. Since there is no output schema, the description adequately covers return values and edge cases.

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

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

Schema description coverage is 100%, so parameters are well-documented in the schema. The description adds extra context for parameters like slippage_pp (explaining zero trading fees and thin depth) and min_partition_leg_kelly (explaining why min_kelly doesn't filter partitions). This adds marginal but useful value beyond schema descriptions.

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

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

The description clearly states it scans top Polymarket markets and returns opportunities where Pipeworx data disagrees with market price. It is built for 'what should I bet on today' and distinguishes from siblings like polymarket_arbitrage and polymarket_edge_tracker by focusing on edge detection across multiple model families.

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 it is for 'what should I bet on today' and helps agents discover opportunities without paging hundreds of markets. It also mentions Fed bets are excluded from ranking. However, it does not explicitly contrast with sibling tools like polymarket_arbitrage or polymarket_edge_tracker.

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 behavioral traits beyond annotations, including snapshot generation on cache-miss, 60-day TTL, daily vs. intraday decay computation, and full response structure. No contradiction with readOnlyHint, idempotentHint, or destructiveHint.

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, front-loaded with purpose, and every sentence adds value. Despite length, it is concise for the complexity, explaining response fields and limitations without waste.

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

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

Given no output schema, the description thoroughly explains response fields (tracked, expired, snapshot_dates) and limitations (TTL, daily closes). It covers all necessary context for agent invocation.

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

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

The input schema already covers both parameters with descriptions (100% coverage). The description mostly restates schema info (defaults, allowed values) without adding new meaning or syntax details.

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

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

The description clearly states the tool's purpose: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots.' It answers a specific question ('how long has this edge existed and is it shrinking?') and distinguishes from sibling tools like polymarket_edges by focusing on historical persistence.

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

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

The description implies usage for historical edge analysis (contrasting fresh vs. old edges) and hints at when not to use it (e.g., for current edges). It doesn't explicitly state alternatives, but the context with sibling polymarket_edges makes it 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and the description confirms it is a read-only check. It discloses behavioral traits: walks the ladder, returns specific fields like slippage, and warns about partial fills converting arb to unhedged positions. 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 thorough and well-structured with clear sections (REQUIRES, SINGLE-MARKET, BASKET). It is front-loaded with the core purpose. However, it is somewhat lengthy; some return field details could be in an output schema if one existed, but given its absence, the detail is justified.

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 (two modes, many return fields, risk warnings) and the lack of an output schema, the description provides extensive return field lists, edge cases (thin legs, forced directional risk), and usage context. It covers all necessary information for an agent to use the tool correctly.

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

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

Schema description coverage is 100%, so each parameter has a description. The description adds further context: explains how size_usd is interpreted differently for single vs basket, side defaults in basket mode, and constraints (clamp 10-1,000,000). This enriches the schema beyond mere repetition.

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

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

The description clearly states the tool performs a realizable-vs-theoretical edge check against live CLOB order-book depth. It distinguishes between single-market and basket modes, specifying what each returns. It also differentiates from sibling tools by explicitly recommending use before acting on polymarket_arbitrage or polymarket_edges signals.

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

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

Explicitly states when to use: before acting on arbitrage signals or edges trades above $500. It details required parameters (one of market or event) and defaults. It does not explicitly state when not to use, but the conditional usage is clear.

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

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

Goes well beyond annotations (readOnly, idempotent) by explaining compatibility_warning, temporal alignment, skipped counters, and the rarity of tradeable spreads. 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?

Well-structured with headings, but somewhat long. Every sentence adds value, so no waste. Slightly verbose but acceptable for 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?

With no output schema, description fully explains response format: leg-by-leg prices, spread, safety fields. Covers all necessary context for agent invocation.

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

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

Schema coverage is 100% and description adds meaning: explains override behavior, lists allowed topics, and provides examples. Adds value beyond schema.

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

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

The description clearly states the tool computes cross-venue spread between Kalshi and Polymarket for the same resolving question. It distinguishes from siblings like polymarket_arbitrage by focusing on cross-venue comparison. Verb and resource are specific.

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

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

Describes two modes (topic shortcuts vs explicit tickers) and warns that most pre-mapped topics return compatibility warnings. Provides context on when spreads are meaningful vs not. Lacks explicit 'use instead of X' but still 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 indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds value by clarifying scoping (anonymous IP, BYO key hash, or account ID), and pairing with save/delete operations. 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?

Three sentences: first defines core function, second provides usage context with examples, third scopes and pairs with siblings. Front-loaded and every sentence is necessary.

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

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

For a simple tool with one optional parameter and no output schema, the description covers what it does, when to use, scoping, and relationship with siblings. The return value (the saved value or list of keys) is implicitly clear.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaning by explaining the effect of omitting the key (list all keys) and giving concrete examples of what keys might store (ticker, address, research notes), which goes beyond the schema description.

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

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

The description clearly states it retrieves a value saved via 'remember' or lists all keys if omitted. It specifies the resource (saved memory values) and verb (retrieve/list), and explicitly distinguishes from siblings 'remember' and 'forget' by naming them as partners.

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: 'Use to look up context the agent stored earlier...without re-deriving it from scratch.' It also implies when not to use by advising to pair with 'remember' to save and 'forget' to delete, providing clear 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?

Adds value beyond annotations: explains mark_read behavior (flags events as read, next call shows newer), mentions returned fields (source, citation_uri, raw payload), and polling suitability. No contradiction with readOnlyHint, idempotentHint, etc.

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

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

Concise 3-sentence description with clear structure: purpose, returned fields, filtering/mark_read, polling and alternative access. No unnecessary words.

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

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

With no output schema and high schema coverage, description covers essential behavioral details (returned fields, mark_read effect), usage pattern (polls fine, alternative URL), and parameter examples. Complete for complexity.

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

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

Schema has 100% coverage, but description adds example for type (e.g., 'sec_8k'), explains since as ISO timestamp, and clarifies mark_read effect. Provides meaning beyond schema.

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

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

Description clearly states verb (Pull), resource (fired events from subscription feed), and differentiates from siblings like list_subscriptions by focusing on alerts, not subscriptions. Examples of returned fields and filtering options add 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?

Provides usage context: polling works fine, alternative access via URL for scripts/dashboards, and filtering by type and since. Does not explicitly state when not to use or compare to siblings like recent_changes, but gives sufficient guidance.

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

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

Annotations provide readOnly, openWorld, idempotent, non-destructive hints. Description goes beyond by detailing fan-out to SEC, GDELT/GNews (with failover), USPTO (soft-fail), and output structure (changes[], total_changes, citation URIs).

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

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

Description is a single paragraph with clear front-loading of purpose and usage examples. Each sentence adds value, though slightly lengthy for a concise definition.

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

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

Given 3 required parameters, 100% schema coverage, no output schema, the description covers behavior, output structure, sources, fallback, and alternatives comprehensively. No gaps.

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

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

Schema coverage is 100%, baseline 3. Description adds value by explaining type enum only supports 'company', giving examples for since (ISO date, relative shorthand, typical '30d'), and clarifying value accepts ticker or CIK.

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

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

Description explicitly states the tool provides a 'change feed for a company in the last N days/weeks/months in ONE parallel call', with verb 'get changes' and resource 'company changes'. It diverges from sibling 'entity_profile' which is for static profiles.

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 example queries ('What's new with X', 'latest on Y', etc.) and explicitly states when to use entity_profile instead: 'Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.'

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 show idempotentHint=true, readOnlyHint=false. Description adds scoping by identifier, persistence differences (authenticated vs anonymous 24h), and pairing behavior. No contradiction.

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

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

Front-loaded main purpose, then usage, then technical details. No wasted words, though slightly verbose with examples.

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 key-value tool with 2 well-documented params and no output schema, description covers purpose, usage, persistence, and integration with sibling tools adequately.

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

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

Schema coverage is 100% with clear descriptions. Description adds examples (e.g., 'subject_property') but does not significantly extend beyond schema. Baseline 3.

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

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

Clear verb+resource: 'Save data... to reuse later.' Distinguishes from siblings 'recall' and 'forget' by explicitly naming them.

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

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

Provides explicit when-to-use (discover something worth carrying forward) and mentions pairing with recall/forget. Lacks explicit when-not-to-use, but context is sufficient.

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

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

Annotations already declare the tool as readOnly, openWorld, idempotent, and non-destructive. The description adds valuable behavioral context: 'Each call cascades through several lookup endpoints internally — using resolve_entity replaces 2-3 manual lookups', providing efficiency insight 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 concise yet comprehensive, front-loading the purpose with example queries and clearly separating type-specific details. Every sentence adds value, maintaining a logical flow without redundancy.

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

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

Despite no output schema, the description fully explains return values for both types, usage context, and behavioral traits. Given the tool's simplicity (2 params) and strong annotations, the description is complete and leaves no gaps for an AI agent.

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

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

Schema coverage is 100% with descriptions for both parameters. The description significantly enriches the schema by detailing what each type returns (e.g., 'returns ticker + 10-digit CIK + company_name' for company) and acceptable value formats, adding critical semantic meaning.

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

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

The description clearly states the tool resolves names to official identifiers, with specific examples ('ticker', 'CIK', 'RxCUI') and use-case phrases. It effectively distinguishes itself from sibling tools by describing its unique purpose of converting human-readable names to IDs required by other 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?

Explicit guidance 'Use FIRST whenever you have a name but need an ID' is provided. While it does not list alternatives or when not to use it, the description's clarity and the unique nature of the tool make this acceptable. The context of replacing manual lookups further guides usage.

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

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

Annotations already indicate readOnlyHint, idempotentHint, and non-destructive behavior. The description adds valuable detail: it probes each entity with ai_visibility_check, returns a ranked list with scores, confidence, and signal density. No contradictions; openWorldHint suggests external API calls are expected.

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

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

The description is three sentences, front-loading the main action and purpose. Every sentence is meaningful: what it does, how it works, example use case, and output format. No wasted words.

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

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

Given no output schema, the description adequately describes the return: ranked list with score, confidence, signal density per entity. The use case and entity role are explained. Minor omission: no mention of error handling or rate limits, but sufficient for typical use.

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

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

Input schema has 100% coverage with descriptions for all parameters. The description adds context not in the schema, like treating the first entity as the subject and that models defaults to workers-ai. This enhances understanding 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 compares AI visibility across multiple entities side-by-side using ai_visibility_check, ranks them, and surfaces the most and least recognized. It distinguishes itself from the sibling ai_visibility_check (which probes a single entity) by explicitly stating it handles multiple entities and produces a comparative 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?

The description provides a specific use case: competitive AI-marketing audits to compare brand recognition. It implies use for multiple entities and that the first entity is the subject, but does not explicitly state when not to use or offer alternatives like compare_entities. Nevertheless, the context is clear.

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

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

Annotations declare read-only, idempotent, open-world hints. Description adds critical behavioral details: composite fan-out, bundlephobia's potential 5-30s delay on first measurement, graceful degradation with sources_failed, and output summary fields. 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?

Single well-structured paragraph, front-loaded with purpose, then details, then usage notes, limitations, and degradation behavior. Every sentence provides essential information; no filler. Concise yet comprehensive.

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 all necessary context: composite nature, services used, default behavior, ecosystem limitation, partial failure handling, and summary fields. The agent has sufficient information to decide when and how to invoke this tool.

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

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

Schema coverage is 100% with descriptions for both parameters. Description adds context beyond schema: it explains the default behavior for version (latest when omitted) and that scoped packages are accepted. This enhances understanding 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 as a composite check for npm package evaluation, specifying the verb 'scan' and resource 'dependency'. It distinguishes from sibling tools by outlining the unique composite behavior (deps.dev + bundlephobia) and the specific question it answers ('is X safe / popular / small').

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: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me".' Also gives clear exclusions: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly.' This provides strong guidance versus alternatives.

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

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

Annotations already declare safe and idempotent behavior. The description adds significant behavioral details: chunking with 500-char overlapping windows, BGE-base-en embeddings, cosine similarity, truncation at 200K chars with flagging, and character offsets for verification. 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 about 5 sentences with the main purpose front-loaded. It efficiently covers usage, pairing, and technical details without excessive verbosity. Could be slightly tighter, but it remains clear and informative.

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

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

For a tool with 3 parameters, no output schema, but strong annotations, the description fully explains the embedding methodology, truncation behavior, offset feature, and pairing advice. An agent can correctly decide to use it and invoke it without missing critical context.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by providing examples for the query parameter (e.g., 'supply-chain risk') and notes the truncation limit for text. This enhances understanding 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 it performs semantic search inside a fetched record. It specifies the verb (search) and resource (a fetched record like SEC 10-K, article, tool result), and differentiates from siblings by mentioning pairing with ask_pipeworx_grounded and use case for large records.

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

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

It explicitly says when to use: 'when the record is too big to cram into the prompt'. It also provides a paired tool recommendation (ask_pipeworx_grounded). It does not list alternatives or when not to use, but the context is clear.

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

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

The description discloses key behavioral traits beyond annotations, such as the requirement for a Pipeworx OAuth account, phone verification for SMS, a 10/day SMS cap, and webhook auto-disable after failures. 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 front-loaded with the core purpose and then provides dense but valuable details. While it is a single paragraph, every sentence adds information; minor redundancy could be trimmed without loss.

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

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

Given the complexity of 3 parameters with nested objects and no output schema, the description covers return value (subscription id), prerequisites, type-specific params, and delivery behavior. Missing explicit return format beyond id, but adequate for agent selection.

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

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

The description adds significant value over the input schema by providing concrete examples for each subscription type's parameters and detailed explanations for delivery channels (email, SMS, webhook with HMAC signing). Schema coverage is 100% but description enriches understanding.

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

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

The description explicitly states the tool's function: 'Create a proactive monitoring subscription to a live-data event stream. Returns the new subscription id.' It clearly distinguishes from siblings like list_subscriptions and unsubscribe by focusing on creation and providing details on subscription types.

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 thorough guidance on when to use each subscription type (e.g., sec_8k for 8-K filings, fred_series for FRED observations) and delivery channels. However, it lacks explicit contrast with sibling tools like recent_alerts, though the purpose is implicitly 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 readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=true. The description adds valuable behavioral details: it returns category-bucketed examples with tool+argument shapes, can be called with no arguments or a topic filter, and describes the output structure. No contradiction.

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

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

The description is slightly long (3-4 sentences) but front-loads the key purpose. Every sentence adds value; minor redundancy could be trimmed but overall well-structured.

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

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

No output schema exists, but the description thoroughly explains the return format (category-bucketed example questions with exact tool+argument shapes). For an onboarding tool, this is complete and leaves no ambiguity about what to expect.

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

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

Schema coverage is 100% with a single optional parameter. The description enriches the schema by listing the allowed topic values (finance, pharma, etc.) and explicitly states that omitting the parameter returns a cross-category spread, which is not in the schema.

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

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

The description clearly states it's an onboarding entry point that returns category-bucketed example questions. It uses specific verbs like 'returns' and 'use this FIRST', and distinguishes itself from sibling tools by describing its role as the starting point for exploring Pipeworx capabilities.

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

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

Explicitly instructs to 'Use this FIRST when you do not yet know what Pipeworx can do for you' and provides trigger phrases. While it doesn't list when not to use it, the context is clear enough for an agent to decide.

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 significant behavioral context beyond annotations: ownership enforcement, deactivation (not deletion), and historical data retention. This aligns with annotations (destructiveHint false, readOnlyHint false).

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

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

Two sentences with no redundancy. First sentence states action and constraint, second explains the effect. Every word serves a purpose.

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

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

For a simple one-parameter tool with good annotations, the description covers ownership, deactivation, and historical event retention. Minor omission: error conditions or prerequisites (e.g., must have an active subscription) are not mentioned.

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 fully describes the only parameter (id as uuid). The description mentions 'by id' but does not add substantial new meaning beyond the schema.

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

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

The description clearly states the tool cancels a subscription by ID, with ownership enforcement and deactivation semantics. It distinguishes from the sibling tool 'subscribe' and explains historical events stay available via 'recent_alerts'.

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

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

The description implicitly indicates when to use (to cancel your own subscription) and mentions historical events remain via recent_alerts, but does not explicitly contrast with other tools like list_subscriptions or subscribe.

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

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

Annotations (readOnly, openWorld, idempotent, non-destructive) are reinforced and extended by the description, which details the dual pipeline (SEC EDGAR for financial claims, grounded pipeline for others), the percent-delta math, and the verdict types. No contradiction.

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

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

The description is somewhat long but efficiently packed with critical information, front-loaded with query patterns. Every sentence is informative. Minor redundancy in listing example queries, but overall well-structured.

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

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

For a tool with only 2 parameters and no output schema, the description is remarkably complete. It explains the two processing paths, the return format (verdict, value, reasoning), and even notes the efficiency gain (replaces 4-6 calls). No gaps.

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

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

Schema coverage is 100%, so baseline is 3. The description adds significant value for 'tolerance_pct' by explaining its use in hallucination detection and default behavior (implied by wording, capped at 5). For 'claim', it gives example formats, exceeding schema description.

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

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

The description clearly states that the tool verifies factual claims against authoritative sources, with specific examples of usage patterns like 'Is it true that...' and 'fact check'. It distinguishes from siblings by emphasizing that it replaces 4-6 sequential calls and handles claim verification end-to-end.

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 whenever the agent needs to check whether something a user said is factually correct.' Describes different paths for financial vs other claims, but could be more explicit about when not to use (e.g., for subjective questions). Still clear overall.

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