Entertainment Feeds

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

Annotations already cover readOnly, idempotent, non-destructive, and open-world. The description adds beyond annotations: it discloses cost implications ('free' vs. 'you pay Anthropic directly'), specifies return structure (per-model {score, confidence, signals, raw_response} + combined), and notes the default model. 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 (four sentences) and well-structured. It front-loads the core purpose and key details (scoring, default model, cost). 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 4 parameters, no output schema, and no nested objects, the description fully covers tool behavior: what it does, which models, cost, parameter roles, and return format. It is complete for an agent to select and invoke correctly.

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

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

Schema description coverage is 100%, so the schema already documents each parameter. The description adds further context: default model is Workers AI Llama-3.3-70b (free), and explains when _apiKey is needed and that it's passed straight through. This enriches 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 probes LLMs for knowledge about a business/brand/product/topic and scores visibility (0-100) per model. It uses a specific verb ('probe','score') and identifies the resource (LLMs, visibility). The purpose is distinct from sibling tools like entity_profile or scan_competitor_ai_presence.

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

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

The description lists explicit use cases: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.' It also notes the default model and that an API key is optional for Anthropic. However, it does not explicitly state when not to use or suggest alternatives, but the provided siblings and context compensate.

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, etc. The description adds valuable context: that it returns structured answers with stable pipeworx:// citation URIs, and that it routes to appropriate tools. 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 detailed but well-structured, with clear sections for usage guidance and examples. While slightly long, every sentence adds value. Front-loads key message to prefer over web search.

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 (huge number of sources) and lack of output schema, the description provides adequate context about capabilities, return format, and when to use alternatives. Covers the essentials without being overly verbose.

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 parameters described as aliases for 'question'. The description does not add additional parameter semantics beyond what the schema provides, so baseline 3 is appropriate.

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

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

The description clearly states it routes questions to 4,774 tools across 1,242 sources for authoritative structured data. It gives specific use cases (SEC filings, FDA, etc.) and contrasts with sibling tools, making the purpose unambiguous.

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

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

Explicitly says 'PREFER OVER WEB SEARCH' and provides detailed when-to-use guidance, including examples of when to step up to ask_pipeworx_grounded or deep_research. Also gives example queries, making it easy for the 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, open-world, idempotent, non-destructive. Description adds valuable context: extra LLM call cost, refusal reasons, extraction from tool result only, and 'hallucination-resistant' guarantees. No contradiction.

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

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

Single paragraph, front-loaded with core purpose. Each sentence adds value (process, return format, use cases, cost). Slightly long but efficient given 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?

Despite no output schema, description covers return structure (answer, evidence, confidence, source, etc.), refusal reasons, and cost trade-off. Fully adequate for agent to decide and 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% with descriptions for all parameters. Description mentions aliases but adds minimal extra meaning beyond schema. Baseline 3 is appropriate.

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

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

Description clearly states it's a hallucination-resistant answer mode for high-stakes reads, distinguishes from sibling ask_pipeworx by noting extra cost and specific use cases like financial verdicts, legal claims, medical 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 specifies when to use: when answer will be quoted/cited/acted on and agent must not invent facts. Also advises preferring ask_pipeworx for casual lookups, 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?

Annotations already indicate read-only, idempotent, non-destructive. The description adds extensive behavioral context: resolution process, classifier system, fan-out examples, response shapes, safety mechanisms (low-confidence short-circuit, closed market handling, wide spread warnings), and resolution-rule risk. This goes well 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?

Very detailed but well-structured with section headers. However, excessively long with many examples and peripheral details that could be condensed. Front-loads the core purpose but some sentences 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 tool's complexity (multi-source fan-out, classifiers, safety checks, resolution details), the description is remarkably thorough. It covers inputs, processing, output structure, edge cases, and errors. Without an output schema, it fully describes return shapes.

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

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

Schema coverage is 100%, baseline 3. The description adds value by explaining depth options ('quick' vs 'thorough' with fan-out extent) and include_raw's impact on response size. This clarifies trade-offs beyond the schema's descriptions.

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

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

The description clearly states the tool researches a Polymarket bet by pulling relevant data in one call. It specifies input types (slug, URL, question) and distinguishes itself from siblings like polymarket_edges by focusing on evidence aggregation and market-vs-model comparison.

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

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

Explicitly says 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z".' It provides clear context but does not explicitly exclude other uses or mention when not to use it relative to 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 indicate read-only, idempotent, and open-world behavior. The description adds value by detailing handling of off-calendar fiscal years, sorting by primary metric, and return format (paired data + citation URIs). No contradictions with annotations.

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

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

The description is well-structured with front-loaded trigger phrases, then entity-type-specific details. It is slightly lengthy but every sentence adds value; minor trimming could be possible without losing clarity.

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

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

Given no output schema, the description thoroughly explains return format (paired data + citation URIs) and covers complexity of two entity types with different data sources and sorting behavior. It is complete for effective usage.

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

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

Schema coverage is 100% but the description adds context: explains that 'values' for company are tickers/CIKs and for drug are names, enforces 2-5 items, and clarifies that results are sorted by primary metric. This goes beyond the schema's parameter descriptions.

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

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

The description clearly states the tool performs side-by-side comparison of 2-5 companies or drugs in a single parallel call. It lists trigger phrases and distinguishes it from sibling tools like entity_profile by emphasizing efficiency 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 explicitly says 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' It provides clear context for use (comparison of entities) and specifies entity types and data sources, offering direct guidance on when to use this tool.

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

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

Annotations already declare readOnly, openWorld, idempotent, non-destructive. Description adds significant context: not open-web search, returns gaps[] for unanswered facets, never invents, expected 15-60s, account required. No contradictions.

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

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

Description is informative and front-loaded with critical prerequisites (account, alternative). Slightly lengthy but every sentence adds value given tool complexity. No fluff.

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

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

Despite no output schema, description fully explains return format: findings packet with evidence, confidence, source, fetched_at, pipeworx:// citation, and gaps[]. Also covers timing and account requirements. Complete for an agent to invoke.

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 depth semantics (quick=3, standard=5, thorough=8 paid) and clarifies question can be broad/multi-part. This adds value beyond the schema's 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 it performs grounded multi-source research across 1242 structured data sources, decomposing questions into facets and routing to 4774 tools in parallel. It distinguishes from sibling 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?

Explicitly tells when to use (broad/multi-part questions over structured data) and when to use alternatives (ask_pipeworx for single lookup or breaking news). Also mentions account requirements and paid plan for 'thorough' depth.

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, revealing it is a safe, read-only, idempotent operation. The description adds significant behavioral details beyond annotations: it explains that results include 'names, descriptions, and full input schemas (with curated examples)' and that each result is 'ready to call directly, no second schema lookup needed.' This helps the agent understand the output structure and readiness for use, though it doesn't describe edge cases or failure modes.

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

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

The description is a single paragraph of 4 sentences, yet it packs essential information: purpose, scope, output format, and usage guidance. Every sentence contributes meaning. It is front-loaded with the core purpose ('Find tools by describing the data or task') and progressively adds detail. 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 the tool's complexity (discovery over many domains), the rich schema and annotation coverage, and the absence of an output schema, the description is complete. It covers purpose, when to use, what results contain, and provides examples. The agent can fully understand how to invoke the tool and interpret its output without additional documentation.

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

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

The input schema has 100% coverage with descriptions for all 6 parameters. The description adds value by clarifying that 'query' accepts natural language and that multiple aliases (task, q, description, search) are accepted. This simplifies parameter usage for the agent. However, the description does not elaborate on the specific semantics of each alias beyond the schema, so it adds moderate additional 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's purpose: 'Find tools by describing the data or task.' It then lists numerous specific data/task categories (SEC filings, financials, FDA drugs, etc.), which concretely defines the scope. This distinguishes it from sibling tools that are more focused on specific data sources or actions (e.g., compare_entities, deep_research). The verb 'discover' and the explicit list of domains make the purpose highly specific.

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

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

The description explicitly tells agents when to use this tool: 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' It also implicitly indicates when not to use it (if you already know the specific tool). The listing of many data/task categories provides clear context for applicability. No explicit alternatives are listed, but the sibling tools are specific and this tool is meant to discover them, so guidance is sufficient.

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

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

Annotations already show safe read-only, idempotent behavior. Description adds valuable context: fans out across sources, mentions USPTO soft-failure, and lists exact return fields. 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 somewhat lengthy but front-loaded with user queries. Every sentence provides value; however, it could be slightly more structured (e.g., bullet list of returns) without losing information.

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

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

Given no output schema, description fully covers all returned fields (cik, company_name, filings, fundamentals, patents, news, LEI) and notes status of each source. Completely adequate for an agent to invoke correctly.

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

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

Schema coverage is 100%, but description adds meaning beyond schema: explains type enum only 'company', value can be ticker or zero-padded CIK, explicitly excludes names, and provides examples.

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

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

Description clearly states it produces a full cross-source profile of a US public company in one call, with examples and explicit verb+resource. Distinguishes from sibling tools like resolve_entity.

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

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

Explicitly says 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups' and warns names not supported, directing to resolve_entity first. Provides clear when-to-use and when-not-to-use.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive. The description adds value by explaining the CF-robust fallback behavior and normalization, which are not in annotations. However, it omits details like error handling, rate limits, or return format.

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

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

Two sentences: the first immediately conveys core purpose, the second adds critical operational details and a sibling pointer. Every sentence contributes 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 complexity (fetching arbitrary feeds, normalization, filtering) and the absence of an output schema, the description is somewhat incomplete. It does not explain the return structure, error scenarios, or limitations (e.g., size limits). The annotations cover safety well, but the description could compensate more for missing output schema.

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

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

Schema coverage is 100% with clear descriptions for all three parameters (url, limit, query). The description does not add substantial extra meaning beyond what the schema already provides, so baseline 3 is appropriate.

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

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

The description clearly specifies the action ('Fetch and normalize') and resource ('any RSS / Atom / RDF feed by URL'). It also differentiates from siblings like list_feeds (curated sources) and read_feed (likely subscribed feeds).

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 an alternative ('Use list_feeds first for curated sources') and provides context for the tool's robustness (CF-robust, fallback proxy). This helps an agent decide when to invoke this vs other feed 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?

Description correctly indicates a destructive action ('Delete'), matching annotations (destructiveHint=true, readOnlyHint=false). No contradiction. Adds context about clearing sensitive data, providing behavioral 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?

Two sentences: first states the action, second gives usage guidelines. No wasted words. Front-loaded with core purpose.

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

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

For a simple single-parameter tool with no output schema, the description is complete. It explains action, usage, and sibling tools. Annotations provide additional safety/behavioral info.

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

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

Schema covers the single parameter 'key' with description 'Memory key to delete' (100% coverage). The description does not add further parameter semantics beyond what the schema provides, so baseline 3 is appropriate.

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

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

The description clearly states 'Delete a previously stored memory by key.' This is a specific verb-resource pair. It distinguishes itself from siblings 'remember' and 'recall' by explicitly mentioning pairing with them, indicating it is the delete counterpart.

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

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

Provides explicit when-to-use guidance: 'Use when context is stale, the task is done, or you want to clear sensitive data.' Also mentions pairing with remember and recall, indicating 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, openWorldHint, idempotentHint, and destructiveHint=False. The description adds behavioral details: fetches page, extracts title/description/key links, emits standard markdown format. This goes beyond annotations to explain process and output structure.

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 with no wasted words. The first sentence states purpose and audience, the second explains process and output, and the third lists use cases. It is front-loaded and 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 two simple parameters, annotations covering safety, and no output schema, the description explains input (URL, optional max_links), process (fetch, extract), output (text blob in llms.txt format), and deployment location (site-root). It also lists use cases. No missing information for a straightforward read-only 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 description coverage is 100% with both parameters (url and max_links) having clear descriptions. The description does not add new parameter-level meaning beyond stating the max_links default and max, but it provides context on how the output is generated. Baseline 3 is appropriate as the schema does the heavy lifting.

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

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

The description clearly states the tool generates a production-ready llms.txt file for any URL, specifying the verb 'generate' and resource 'llms.txt file'. It also lists AI crawlers that benefit, making the purpose distinct from sibling tools which focus on other tasks like research or feeds.

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 use cases are provided (indexing client sites, drafting for own projects, auditing competitors). It tells when to use the tool but does not mention when not to use it or suggest alternatives among siblings, though no siblings overlap directly.

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, so the description's main behavioral addition is the expected output fields. No mention of pagination or ordering, but this is acceptable given the annotations provide safety context.

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

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

The description is two sentences, front-loaded with purpose, and every part is informative. No redundant or extraneous wording.

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

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

For a simple list tool, the description covers the returned fields, optional filters, and links to read_feed for detail. Lacks pagination info, but the tool appears small enough that this is not critical.

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

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

The input schema already provides descriptions for both parameters at 100% coverage. The description repeats the filter options but does not add new information or clarify behavior beyond what the schema states.

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

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

Description clearly states it lists curated entertainment & culture feeds and specifies the returned fields (id, title, category, source). It distinguishes from sibling tools like read_feed by advising to pass an id to read_feed, and from list_subscriptions by focusing on feed listing rather than subscriptions.

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

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

Description indicates optional filters by category or keyword and explicitly recommends using read_feed for a specific feed. However, it does not contrast with other sibling tools like list_subscriptions, leaving some inference required.

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

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

Annotations already declare readOnly, idempotent, not destructive. Description adds that it returns caller-specific data and lists specific fields, confirming safety and providing additional 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?

Two sentences with no wasted words. Front-loaded with purpose, then returns fields, then usage advice. Ideal conciseness.

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

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

No output schema, so description compensates by enumerating return fields. Includes usage context. Slightly lacking details like pagination or default sorting, but sufficient for a simple list tool with good annotations.

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

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

Schema coverage is 100% with a clear description for the only parameter. The tool description does not add new meaning beyond the schema's parameter description, so baseline 3 is appropriate.

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

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

Description clearly states verb 'List' and resource 'the caller's active subscriptions', distinguishing it from sibling tools like subscribe and unsubscribe. Enumerates return fields, leaving no ambiguity about what it does.

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

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

Explicitly says to use this 'before adding more' subscriptions or 'to find an id to cancel', providing practical when-to-use guidance. Lacks explicit when-not-to-use or comparison with alternatives, but context is clear enough.

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: rate-limited to 5 per identifier per day, free, doesn't count against quota. Annotations indicate readOnlyHint=false (mutation) and destructiveHint=false, which are consistent. 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 and well-structured, with the purpose front-loaded. Every sentence provides value: specifying when to use, what not to do, and behavioral notes. 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 explains what happens after submission (digests daily, roadmap impact) and covers rate limits, usage context, and parameter details. It is complete for a feedback submission 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 description coverage is 100%, so the schema already documents each parameter. The description adds little beyond the schema for parameter semantics, though it reiterates the type enum and message constraints. The note about not pasting the end-user's prompt is a usage guideline, not parameter semantics.

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

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

The description clearly states the tool's purpose: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It uses a specific verb ('tell') and resource ('Pipeworx team'), and distinguishes from sibling tools by focusing on feedback versus queries or other actions.

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 specifies when to use the tool (bug, feature, data_gap, praise) and when not to (don't paste the end-user's prompt). It also provides context such as daily digests and roadmap impact, giving clear guidance on usage compared to 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, openWorldHint, idempotentHint, and destructiveHint. The description adds non-obvious details: data source (CF analytics-engine), no PII, cached 5min-1h depending on window. 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?

Four sentences, front-loaded with the return value, uses bullet-like enumeration for use cases. Every sentence contributes meaningful info; 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?

Although no output schema, the description explains the output structure (top tools, top packs, total call volume) and adds context about data source and caching. This is complete for a simple query tool.

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

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

Schema coverage is 100% with a description on the 'window' parameter. The description adds guidance on choosing window for different needs (hot vs. steady-state), going beyond the schema's enum listing.

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

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

The description clearly states the tool returns top tools, top packs, and total call volume over a window (24h, 7d, 30d). It provides specific use cases (discovering hot data sources, confirming canonical choices, seeing alignment) and differs from siblings like discover_tools by focusing on trending query data.

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

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

The description includes three explicit use cases and advises on window selection (shorter windows for current hotness, longer for steady-state). It lacks explicit when-not-to-use guidance but is sufficient given the read-only nature and context from sibling tool list.

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

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

The description discloses extensive behavioral details beyond annotations: it explains monotonicity violations, partition-sum checks, Jaccard similarity filter, placeholder filtering, fill check with live depth, and when not to trade. All annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint) are consistent with the described behavior.

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

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

The description is well-structured with a clear front-loaded purpose sentence, then ordered by modes and details. It is somewhat lengthy but every sentence adds necessary detail. A slightly more concise presentation could improve scannability, but it remains effective.

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

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

Given the tool's complexity (three modes, multiple check mechanisms, fill validation) and the absence of an output schema, the description covers all essential aspects: response fields, edge cases like skipped_low_similarity and placeholder filtering, and the fill check logic. It is contextually complete for an AI agent to understand and 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 coverage is 100% and each parameter has a description. The tool description adds value by explaining that 'event' accepts full URLs and providing example slugs, as well as describing what 'topic' seeds (a seed question) and how it searches related events. This goes beyond the schema but the schema already provides sufficient 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's purpose: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It distinguishes the three modes (trending_scan, event, topic) with specific use cases, distinguishing it from sibling tools.

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

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

The description explicitly tells when to use each mode: 'Call with NO args for a trending_scan... pass event for... or topic for...' It also recommends using event for a specific market and advises using polymarket_fill_risk for custom sizing, providing clear guidance on 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 declare readOnlyHint=true, idempotentHint=true, etc., and the description goes far beyond by detailing caching (1h at KV level), edge calculation with slippage, per-leg Kelly filtering, and diagnostics for empty segments. No contradiction with annotations; adds rich behavioral context.

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

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

The description is lengthy but well-structured into logical sections (model families, tradeable-edge knobs, response structure). Every sentence adds value given the tool's complexity. Could be slightly more concise, but the detail is justified for a tool with 9 parameters and multiple output segments.

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 specifies the response structure (by_segment, fed_candidates, _diagnostics) and explains why segments may be empty. Covers caching, edge calculation, and filter interactions. Highly complete for a complex tool with zero output schema requirements.

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 9 parameters described. The description adds valuable context beyond the schema, explaining parameter interactions (e.g., min_partition_leg_kelly vs min_kelly), default values, and practical trade-offs (e.g., slippage explanation). A slight deduction because some parameter descriptions are lengthy but still clear.

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

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

The description clearly states the tool scans Polymarket markets and returns opportunities where Pipeworx data disagrees with market price. It specifies the verb 'scan' and resource 'Polymarket markets', and distinguishes from siblings by detailing three model families (model_driven, structural_arbitrage, concentrated_longshot) that are unique to this tool.

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

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

Explicitly positioned for 'what should I bet on today' and mentions agents can discover opportunities without paging hundreds of markets. Discusses tradeable-edge knobs like min_liquidity and max_spread_pp to filter realizable edges. However, does not explicitly contrast with sibling tools like polymarket_arbitrage or polymarket_edge_tracker, which would help in selection.

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

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

Annotations already indicate read-only, open-world, idempotent, and non-destructive. The description adds substantial behavioral details: response structure (tracked[], expired[], snapshot_dates[]), limits (60-day TTL), and decay computation method (daily closes). 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 lengthy but well-organized: purpose, input args, response fields, limits. Every sentence provides value, though some could be merged for brevity. It is front-loaded with the core question.

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

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

No output schema exists, so the description must explain the return values. It thoroughly describes tracked[], expired[], and snapshot_dates[] fields, including edge_pp_net time-series, trend, decay_pp_per_day, lifespan_days, and snapshot gaps. Limits are also noted. 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 description coverage is 100%, baseline 3. The description adds context: default values, maximum days, snapshot family notation, and explanation of the 'window' parameter. This adds meaningful semantic nuance beyond the schema.

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

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

The description clearly states the tool's purpose: providing edge persistence and decay telemetry from daily snapshots. It uses specific verbs like 'Answers' and explains the value proposition with examples, distinguishing it from the sibling polymarket_edges.

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

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

The description gives clear context on when to use this tool: to differentiate between fresh and aged edges. It implies usage over polymarket_edges but does not explicitly state exclusion criteria, though the context is sufficient.

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

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

Annotations already mark readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds behavioral details: walks the order book ladder, returns verdict (clean|degraded|cannot_fill), per-leg fill details for baskets, and warns about forced directional risk and stranded legs. 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?

While the description is lengthy, it is well-structured with capital letters for key terms (REQUIRES, SINGLE-MARKET, BASKET) and clear sections. Every sentence adds value, but could be slightly more concise. Still very effective for the complexity.

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

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

Given no output schema, the description thoroughly enumerates return fields and their meanings for both modes. It covers edge cases (thin legs, forced directional risk) and provides a decision framework (verdict). Completes the tool's behavior description comprehensively.

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 context beyond schema: it explains how size_usd is interpreted differently for single-market (spend/proceeds) vs basket (settlement notional), the auto side logic for baskets, and default values. This extra context justifies a score above baseline.

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

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

The description explicitly states it performs a 'realizable-vs-theoretical edge check against live CLOB order-book depth' and distinguishes between single-market and basket modes, listing specific return fields. It differentiates from sibling tools by advising use before polymarket_arbitrage or polymarket_edges actions, providing clear purpose differentiation.

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

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

Provides explicit guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500'. Explains why (theoretical overround on thin books is not capturable, partial fills create directional risk). Also notes requirement of either market or event parameter.

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 (readOnlyHint, idempotent, openWorld), the description details response structure, safety fields, and edge cases like non-equivalent bet shapes and temporal misalignment. Explains counters and when no arbitrage exists. 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?

Well-structured with clear sections (TWO MODES, RESPONSE, SAFETY FIELDS). Front-loaded with purpose. While longer than minimal, the complexity of the tool justifies the length. No wasted sentences, but 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?

Given no output schema, the description fully covers return values (leg-by-leg prices, spread, safety fields) and edge cases (compatibility_warning, temporal_alignment). Explains what the tool does in all scenarios, including when it says 'no arb exists'. Complete for a complex tool.

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

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

Schema already describes all 3 parameters (100% coverage). Description adds value by explaining the dual-mode behavior: topic acts as a shortcut mapping, and explicit parameters override. Enriches understanding beyond schema descriptions, though schema already provides basic semantics.

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

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

The description clearly states the tool's purpose: computing cross-venue spread between Kalshi and Polymarket for the same resolving question. It distinguishes from siblings like polymarket_arbitrage by focusing on two-venue comparison rather than single-venue arbitrage. Specific verb 'compute spread' and resource 'same resolving question' makes it unambiguous.

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

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

Explicitly describes two modes (topic shortcuts vs explicit ticker/slug) and provides guidance on when spreads are meaningful vs not (e.g., compatibility_warning cases, temporal alignment). Warns that most pre-mapped topics return warnings, setting realistic expectations. Tells agent when not to rely on output.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds value by specifying that items are normalized and that keyword filtering is optional. 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?

Two concise sentences front-load the main action and return format. Every word is necessary and there is no fluff.

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

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

The description covers the main functionality, return fields, and optional filtering. It does not mention pagination or limit behavior, but given the schema covers limit, it is sufficiently complete for a read-only tool with strong annotations.

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

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

Schema coverage is 100% with detailed parameter descriptions. The description reinforces the feed id origin and keyword filtering but does not add significant new meaning beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states the verb 'Read', the resource 'curated entertainment & culture feed by its id', and mentions the return format. It distinguishes itself from sibling tools like 'list_feeds' and 'fetch_feed' by specifying the use of a feed id from list_feeds and normalizing items.

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 after list_feeds by stating 'from list_feeds'. It does not explicitly exclude alternatives or state when not to use, but the context is clear enough for a typical agent.

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

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

Annotations already provide read-only and idempotent hints. Description adds scoping to identifier, which is useful 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?

Two concise sentences with no wasted words, front-loaded with the core action.

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, description covers purpose, usage, and behavioral context completely. Output format implied.

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 essential behavior: omitting key lists all keys. Also clarifies scoping.

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

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

The description clearly states the tool retrieves a value saved via remember or lists all keys when omitted. It distinguishes itself from siblings remember and forget.

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

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

Explicitly guides when to use: to look up context stored earlier without re-deriving, and mentions scoping and pairing with remember/forget.

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?

Disclosures beyond annotations: return structure (source, citation_uri, raw payload) and effect of mark_read (flags events as read for next call). Annotations already indicate read-only and idempotent; description adds useful context without contradiction.

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

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

Three sentences, each with distinct purpose: purpose, parameters/return details, and usage notes. No wasted words, front-loaded with key action. Excellent structure.

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

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

Covers return structure, mark_read behavior, and alternative access method. Minor gaps: no explicit order of results, limit parameter behavior (beyond schema), and unread_only parameter not elaborated. Still mostly complete.

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

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

Schema has 100% coverage, so baseline is 3. Description adds context: mark_read effect, type example (sec_8k), and limit range (1-200). 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?

Clearly states the tool pulls fired events from subscription feed, with specific return fields (source, citation_uri, raw payload). It does not explicitly differentiate from siblings like fetch_feed or read_feed, but the filtering and mark_read details add specificity.

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 guidance on when to use filters (type, since) and mark_read, and mentions an alternative endpoint (direct GET) for scripts/dashboards. Lacks explicit when-not-to-use or comparison to sibling tools.

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

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

Beyond the annotations (readOnly, idempotent, openWorld), the description discloses fan-out to multiple sources, GNews fallback on rate limits, and USPTO soft-fail due to sunset. This provides rich behavioral context.

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

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

The description is comprehensive but slightly lengthy. It front-loads with example queries, which is helpful. Every sentence adds value, though some redundancy exists (e.g., repeating the same idea in different example phrases).

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

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

Given no output schema, the description explains the return structure (changes grouped by source, total_changes count, citation URIs). All key aspects (parameters, sources, fallback, alternative tool) are covered, making it self-sufficient.

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

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

Schema description coverage is 100%, but the description adds value with examples of since formats (ISO date, relative shorthands) and clarifies value accepts ticker or CIK. This goes beyond the schema's basic descriptions.

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

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

The description clearly states that the tool provides a change feed for a company over a time window, with specific sources (SEC, GDELT/GNews, USPTO). It explicitly distinguishes from the sibling tool entity_profile, which provides 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?

The description gives example queries and explicitly tells when to use entity_profile instead. However, it does not mention other potentially relevant siblings like deep_research, but the guidance is clear for its primary use case.

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 scope by identifier, persistence differences (authenticated vs anonymous with 24-hour retention), and write nature. Annotations consistent with description (idempotentHint=true, destructiveHint=false). 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?

Concise paragraph with front-loaded purpose, each sentence adds necessary context. Slightly verbose with multiple examples but still efficient.

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

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

Given simple schema (2 parameters, no enums, no nested objects, no output schema) and annotations present, the description fully covers usage context, behavioral traits, and lifecycle.

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 provides full coverage of key and value parameters with examples. Description adds minimal extra meaning beyond stating 'scoped by your identifier'. Baseline 3 is appropriate given high schema coverage.

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

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

Description explicitly states 'Save data the agent will need to reuse later' and mentions key-value pair storage across sessions. It distinguishes from sibling tools 'recall' and 'forget'.

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

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

Provides clear guidance on when to use: 'when you discover something worth carrying forward', with examples. Also directs to pair with recall and forget for complementary actions.

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

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

Annotations already indicate read-only, open-world, idempotent, non-destructive behavior. The description adds significant value by revealing that internal calls cascade through several endpoints, replacing 2-3 manual lookups, and detailing the return format (ticker, CIK, citation URI for companies; RxCUI, ingredient, brand for drugs).

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

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

The description is somewhat lengthy but well-structured, with front-loaded purpose and example queries. Every sentence provides essential information without redundancy, though it could be slightly more concise by omitting internal implementation details.

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

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

Given the lack of an output schema, the description adequately explains return values and internal behavior. It covers all necessary aspects for an agent to understand what the tool returns and how it works, making it 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% and the description adds concrete examples and accepted input formats (e.g., ticker, CIK, or name for company; brand or generic name for drug), providing meaning beyond the schema's enum and type constraints.

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

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

The description clearly states the tool resolves user-spoken names to canonical IDs, with specific examples and supported types. It distinguishes itself from siblings by focusing on ID resolution, which is a distinct task compared to entity profiles or comparisons.

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

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

The description explicitly says 'Use FIRST whenever you have a name but need an ID.' This provides clear context for when to use it, but does not mention when to avoid or specify alternatives among siblings, though the uniqueness of the task implies lack of direct substitutes.

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

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

Annotations already indicate read-only, open-world, idempotent, non-destructive. The description adds that it probes each entity with ai_visibility_check, ranks by score, and returns a ranked list with score, confidence, signal density per entity. It also notes the first entity is treated as 'subject'. No contradictions.

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

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

Three sentences, front-loaded with main action and value, no redundant information. Every sentence earns its place.

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

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

Given no output schema, description explains return format (ranked list with score, confidence, signal density). It also covers input constraints (entity count), dependencies (ai_visibility_check, api key for anthropic), and optional parameters. Complete for the tool's complexity.

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

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

Schema coverage is 100% with descriptions for all 4 parameters. The description adds meaning by specifying entities array size (2-8), first entry as 'subject', and that context disambiguates common names, going beyond schema 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 compares AI visibility across multiple entities side-by-side, ranks by score, and surfaces which is most/least recognized. It distinguishes from siblings like ai_visibility_check (single entity) and compare_entities (general comparison).

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

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

The description provides a use case ('competitive AI-marketing audits') and an example question, but does not explicitly state when not to use or list alternatives. Usage is implied rather than explicitly guided.

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

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description adds valuable context: it fans out to external APIs, may experience delays on first measurement, returns partial results on failure, and lists exact return 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?

The description is front-loaded with the core purpose, then efficiently covers usage, return structure, and limitations. Every sentence adds value, and the structure is logical despite its length.

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

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

Given no output schema, the description fully explains return values (summary block fields, per-advisory detail, links, alternative versions). It also covers partial failure behavior, timeouts, and ecosystem scope, making it complete for agent usage.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds minimal parameter-specific information beyond what the schema already provides (e.g., npm ecosystem, version defaults). It provides usage examples but no new semantic constraints.

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

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

The description clearly states the tool's purpose as a composite check for adding an npm package, combining data from deps.dev and bundlephobia. It explicitly distinguishes from siblings by noting it's npm-only and provides concrete usage examples like '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?

The description gives explicit triggers ('Use whenever an agent asks...'), ecosystem limitations ('NPM ecosystem only in v1'), and caveats about timeout and graceful degradation. It tells when to use alternatives (other ecosystems use deps.dev directly).

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 a safe, read-only operation. The description adds critical behavioral details: embedding model (BGE-base-en), similarity metric (cosine), chunking strategy (500-char overlapping windows), character limit (200K), truncation behavior, and output includes offsets and similarity scores. 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 a single dense paragraph with no wasted words. It front-loads the core purpose, then efficiently covers use case, pairing, technical details, and limitations. Every sentence contributes essential information.

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

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

Given the tool's complexity (semantic search, truncation, chunking), the description fully explains input constraints, the algorithm, output format (offsets, scores), and intended usage pattern. Without an output schema, this description provides sufficient context for correct invocation and result interpretation.

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

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

Schema description coverage is 100% with good parameter descriptions. The description enriches them by clarifying the max length of 'text' (200K chars), providing example queries for 'query', and stating the default and range (1-20) for 'limit'. This adds value beyond the schema.

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

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

The description clearly states the tool's function: semantic search inside a fetched document. It specifies verb+resource ('search inside a fetched record') and provides concrete examples (SEC 10-K body, article, long tool result). Mentioning pairing with ask_pipeworx_grounded helps distinguish it from sibling tools.

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

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

The description explicitly advises using this tool when a record is too large for the prompt, saving context. It explains that passages come with offsets for verification, but does not explicitly state when NOT to use it or list alternatives beyond the paired sibling.

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 non-readonly, non-destructive, idempotent, open-world. The description adds valuable context: SMS cap (10/day), webhook auto-disable after 10 failures, one-time secret return, and phone verification requirement. 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 well-structured with a clear intro, requirements, type breakdown, and delivery options. While somewhat long, every sentence adds actionable information. Could tighten slightly but no 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 the tool's complexity (3 params, 2 required, nested objects, no output schema), the description fully explains inputs and behavior. It states the return value ('new subscription id') and covers edge cases like phone verification and webhook signing. Siblings are distinct.

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 enriches each parameter with concrete examples (e.g., items codes, topic 'fed', series_id 'UNRATE'), delivery constraints, and webhook HMAC details. This far exceeds baseline value.

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

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

The description uses a specific verb 'create' and resource 'proactive monitoring subscription to a live-data event stream', clearly distinguishing from sibling tools like list_subscriptions and unsubscribe. It also specifies the return value (subscription id).

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

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

The description explicitly states the requirement for a Pipeworx OAuth account and provides examples of supported types and delivery channels, guiding when to use the tool. However, it does not explicitly state when not to use it or mention alternatives for one-off queries.

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

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

Description adds value beyond annotations by detailing the output format (category-bucketed example questions with tool shapes) and the effect of calling with no arguments vs. topic. No contradiction with annotations (readOnlyHint, idempotentHint).

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: front-loaded with common user questions, then the purpose, return format, and usage. Every sentence serves a purpose, though it 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 and simple parameters, the description fully explains the tool's behavior, return value, and use cases. It covers when to use, what it returns, and how to customize, making it complete for an onboarding 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%, so baseline is 3. Description adds significant value by listing the allowed focus areas and clarifying that omitting the parameter yields a cross-category spread, beyond the schema's 'Optional focus area' 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?

Description clearly states it is the onboarding entry point, returning example questions with tool calls. It specifies the categories (company financials, drugs, etc.) and distinguishes from siblings like discover_tools by focusing on what to ask rather than what tools exist.

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

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

Explicitly advises 'Use this FIRST when you do not yet know what Pipeworx can do' and explains when to pass the topic parameter versus omitting for full spread. No usage exclusions needed.

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 mutability (readOnlyHint=false) and non-destructiveness (destructiveHint=false). The description adds that the row is 'deactivated (not deleted) so its historical events stay available', providing useful behavioral nuance beyond the annotations.

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

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

Two sentences, front-loaded with purpose. Every sentence adds value: purpose, ownership, and deactivation behavior. 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 simple parameter requirements and no output schema, the description covers key behaviors (ownership, soft delete). It could mention return confirmation but is adequate for agent use.

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

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

Only one parameter 'id' with schema description 'Subscription id (uuid) returned by subscribe.' The description does not add new meaning beyond the schema; it only reiterates the source of the id. Schema coverage is 100%, so baseline 3 is appropriate.

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

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

The description clearly states 'Cancel a subscription by id', specifying a specific verb and resource. It distinguishes itself from siblings like 'subscribe' and 'list_subscriptions' by focusing on cancellation.

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?

Ownership enforcement is explicit: 'you can only cancel your own subscriptions', which tells the agent when to use this tool (own subscriptions) and implies not to use for others. It does not explicitly name alternatives but context is clear.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds useful behavioral details: returns verdict types, extracted structured form, actual value with citation, percent delta, and data source (SEC EDGAR + XBRL). It does not contradict annotations.

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

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

The description is a single dense paragraph that front-loads key information with examples and usage guidance. Every sentence adds value, though a more structured format (e.g., bullet points) could slightly improve readability.

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 only one parameter, no output schema, and comprehensive annotations, the description covers domain scope, return values, data sources, and benefit. It lacks error handling details for out-of-scope claims, but overall is adequately complete for this simple 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 description coverage is 100% for the single parameter 'claim'. The description adds value by providing example formats and clarifying the supported claim types, which helps the agent understand expected input beyond the schema's brief 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 performs natural-language claim verification against authoritative sources, with specific examples and domain scope (company-financial claims for public US companies). It distinguishes itself from siblings by explicitly noting it replaces multiple sequential calls.

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

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

The description explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct.' It provides context on when to use the tool, but does not explicitly mention when not to use it or list alternative tools for out-of-scope claims.

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