Federal Register

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

Annotations already declare readOnlyHint=true, openWorldHint=true, etc. The description adds value by explaining the default model (free), the need for BYO key for Anthropic (cost implication), and the output structure (per-model score, confidence, signals, raw_response + combined view). No contradiction with annotations.

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

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

Two sentences with front-loaded action and output. No redundant words. Every sentence adds value: first specifies the core function, second elaborates on models and output.

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 output structure, use cases, and key parameters. It lacks explicit mention of error handling for invalid API keys or rate limits, but given the simple parameters and non-destructive nature, it is 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 description coverage is 100%, so the baseline is 3. The description adds slight context about default model and the role of _apiKey, but does not significantly enhance meaning beyond the already descriptive 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 about a brand/topic and scores visibility (0-100). It uses specific verbs like 'probe' and 'score', and explicitly distinguishes from siblings like 'scan_competitor_ai_presence' by mentioning multi-model probing and scoring.

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

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

The description provides explicit usage scenarios (AI-marketing audits, pre-launch brand checks, competitive monitoring) and explains when to use the _apiKey parameter. However, it does not explicitly state when not to use this tool versus alternatives like 'scan_competitor_ai_presence'.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds value by explaining the routing mechanism (4,774 tools across 1,242 sources), argument filling, and stable citation URIs, which are not covered by annotations.

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

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

The description is somewhat verbose but well-structured, front-loading the most important guidance ('PREFER OVER WEB SEARCH') and using bullet-like structure for examples and step-up recommendations. 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?

For a tool with 6 parameters, no output schema, and no nested objects, the description is comprehensive. It covers purpose, usage, behavioral details, and examples. The mention of structured answers with citations compensates 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 all parameters described as aliases for 'question'. The description provides examples and context but does not add significant semantic meaning beyond what the schema already provides. Baseline of 3 is appropriate.

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

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

The description clearly states it answers questions about current or historical data from multiple sources, using a specific verb ('ask') and resource ('pipeworx'). It distinguishes from siblings like web search, ask_pipeworx_grounded, and deep_research, 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 guidance on when to use (factual questions with examples) and when to step up to alternatives (ask_pipeworx_grounded, deep_research). Includes specific query patterns like 'what is', 'look up', 'find'.

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

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

The description goes beyond annotations (readOnlyHint, etc.) by detailing the underlying process: routing, argument filling, data fetching, and extraction using only tool results. It lists explicit refusal reasons and the extra LLM call cost, providing rich behavioral context.

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

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

The description is thorough and front-loaded with the key purpose. While slightly lengthy, every sentence adds value (purpose, process, examples, cost). Minor verbosity prevents a 5, but it remains efficient and well-structured.

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

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

Given the tool's complexity (multi-step routing, multiple failure modes), the description is comprehensive. It explains the full workflow, return format with refusal reasons, and use cases. No output schema, but description compensates by detailing the return structure. Complete for agent decision-making.

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 parameters well. The description adds minimal extra meaning for parameters (only 'Your question in natural language' and alias listing). Baseline of 3 is appropriate as description doesn't significantly augment parameter understanding.

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

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

The description clearly states the tool's purpose: hallucination-resistant answer mode for high-stakes reads. It explains that it extracts answers only from tool results and specifies the return format. It distinguishes itself from the sibling ask_pipeworx by noting the extra LLM call cost and stricter fact-checking.

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

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

The description provides explicit guidance on when to use this tool: when answers will be quoted, cited, or acted on, and when the agent must not invent facts. It also advises preferring ask_pipeworx for casual lookups due to cost, giving 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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds extensive behavioral details: low-confidence resolution short-circuiting, closed market status, wide spread warnings, and resolution-rule risk. 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 quite lengthy with multiple paragraphs covering examples and edge cases. While front-loaded with the core purpose, it lacks conciseness and could be trimmed. However, it is well-structured with sections, earning a mid-range score.

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 parameters, no output schema), the description is exceptionally complete. It details response shapes, resolver contract, parent event extractor, news fields, safety mechanisms, and resolution-rule risk, leaving no gaps for an agent to misinterpret.

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

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

Schema description coverage is 100%, and the description adds meaning beyond the schema by explaining the 'quick' vs 'thorough' depth behavior, the impact of 'include_raw' on response size, and providing concrete examples for 'market' input. This adds value beyond the schema definitions.

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

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

The description clearly states the tool researches a Polymarket bet by pulling Pipeworx data. It specifies the input types (slug, URL, question text) and distinguishes from sibling tools like polymarket_edges by focusing on a single bet's evidence retrieval.

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

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

The description provides explicit use cases (e.g., 'should I bet on X', 'what does the data say about Y') and explains response shapes and safety mechanisms. However, it does not explicitly mention alternatives or when not to use this tool, slightly reducing clarity.

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 detail beyond annotations: explains that company data comes from latest 10-K, handles off-calendar fiscal years correctly, results sorted by primary metric, and returns 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?

Description is focused and front-loaded with typical queries, but slightly verbose with multiple example phrases. Still efficient overall; 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 no output schema, description explains return value (paired data with citation URIs). Covers both entity types comprehensively. No gaps 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% and description enriches both parameters: explains 'type' values with examples of data pulled, and for 'values' clarifies format (tickers/CIKs for company, names for drug) and bounds (2-5). Adds meaning beyond schema.

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

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

Description clearly states the tool performs side-by-side comparison of 2-5 entities (companies or drugs) and specifies the data sources and metrics for each type. It distinguishes from siblings like entity_profile which handles single entity 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?

Description explicitly says 'ALWAYS PREFER over sequential single-pack lookups when comparing entities' and provides example queries. It tells when to use the tool (comparisons) and implies alternatives (single entity lookups).

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

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

Beyond annotations (readOnly, openWorld, idempotent), the description adds critical behavioral details: account required, paid plan needed for 'thorough', returns findings packet with gaps[], not open-web search, expected 15-60s latency, and that it decomposes questions into facets.

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 packed with useful information but is somewhat lengthy; however, it is front-loaded with the most critical info (account requirement) and every sentence serves a purpose, earning a high but not perfect score for 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?

Given no output schema, the description fully explains the return format (findings packet with evidence, confidence, source, fetched_at, citation, gaps[]) and constraints (15-60s latency, not open-web), making it complete for an agent to understand what to expect.

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

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

Schema coverage is 100%, but description adds significant semantic value by explaining the depth parameter as specific numbers (quick=3, standard=5, thorough=8) and indicating that question should be broad/multi-part natural language, which goes beyond the schema's enum and type 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 this tool performs grounded multi-source research across structured data sources in one call, and distinguishes it from siblings like ask_pipeworx by specifying use cases for broad/multi-part questions vs single lookups or breaking news.

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

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

Provides explicit guidance: use for broad/multi-part structured data questions, use ask_pipeworx for single lookups or breaking/current-news topics, and notes 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, destructiveHint=false, idempotentHint=true. Description adds that results include 'full input schemas (with curated examples)' and are 'ready to call directly, no second schema lookup needed.' This provides useful behavioral context beyond annotations without contradiction.

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

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

Description is front-loaded with the core purpose and includes several specific examples. Sentences are focused and each adds value, though the list of domains could be slightly shortened. Overall efficient for the scope.

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

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

Given this is a simple discovery tool with one required parameter and no output schema, the description covers what the agent needs: what it does, when to use it, and what to expect in return. No major gaps identified.

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 including aliases. Description adds examples of usage but does not provide additional meaning beyond what the schema already conveys. Baseline score of 3 is appropriate.

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

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

Description clearly states 'Find tools by describing the data or task' and lists specific domains (SEC filings, financials, FDA drugs, etc.). It explicitly explains the tool returns top-N relevant tools with full schemas, distinguishing it from sibling tools like search_documents or search_within which act on documents rather than tool discovery.

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

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

Explicitly instructs 'Use when you need to browse, search, look up, or discover what tools exist' and 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This gives clear context for when to invoke this tool versus alternatives.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds valuable behavioral details: fans out across multiple sources, returns specific fields, mentions soft-fail for patents, and fallback for news. 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 relatively long but well-structured with example queries and a bullet-point list of outputs. It is front-loaded with examples, making it easy for an agent to parse. Minor redundancy but overall 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 the tool's complexity and absence of an output schema, the description is remarkably thorough. It details exactly what is returned from each source, including specific fields and URIs. No gaps remain for the agent to guess.

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

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

Schema coverage is 100%. The description reinforces parameter semantics: type enum limited to 'company', value as ticker or CIK, and explicitly states names not supported. This adds useful context 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: generating a full cross-source profile of a US public company. It provides example queries and distinguishes itself from siblings like resolve_entity and deep_research.

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

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

Explicitly states when to use this tool over alternatives ('ALWAYS PREFER over chaining single-pack... when holistic view is needed') and when not to use it (names not supported; use resolve_entity first).

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

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

Annotations already convey destructiveHint=true and idempotentHint=true. Description adds context about clearing sensitive data and usage context, but doesn't 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?

Two sentences, action first, no wasted words. Efficient and well-structured.

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

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

For a simple tool with one required parameter, good annotations, and no output schema, the description provides complete context for appropriate usage.

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

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

Schema covers the single parameter fully with a description. Description adds no additional semantic meaning beyond what's in the schema.

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

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

Description uses specific verb 'Delete' and resource 'memory by key', clearly distinguishing from sibling tools like 'remember' and 'recall'.

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

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

Explicitly states when to use (stale context, task done, clear sensitive data) and advises pairing with siblings, providing clear guidance.

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

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

Adds context beyond annotations: explains the fetch-extract-emit process and that output is a single text blob. Does not detail rate limits or auth, but annotations already cover safety.

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 concise sentences with clear structure: purpose, process, use cases. No wasted words, front-loaded with key info.

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

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

Covers purpose, process, output format, and use cases adequately for a simple generation tool with no output schema.

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

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

Schema coverage is 100%, so baseline 3 applies. Description adds mention of 'any URL' and default/max for max_links, but these are already in the schema.

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

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

Description clearly states verb and resource: 'Generate a production-ready llms.txt file'. It specifies the audience (AI crawlers) and the output format, distinguishing it from sibling analysis 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?

Provides explicit use cases (client indexing, own project, competitor audit) but does not mention when not to use or alternatives like scan_competitor_ai_presence.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering safety and idempotency. The description adds value by listing the returned fields (title, abstract, full text link, agencies, dates, docket information), enriching the behavioral context beyond the annotations. No contradiction exists.

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 extremely concise: two sentences with no fluff. The first sentence clearly states the action and input, the second lists the output. Every word serves a purpose, earning top marks in 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?

Given the tool's simplicity (one parameter, output schema present), the description is fully complete. It explains the input format, the purpose, and the key output fields. The output schema handles detailed return values, so the description's summary is 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%, so the baseline is 3. The description provides an example document number and summarizes the output, but does not add significant semantic meaning about the parameter beyond what the schema already provides. It is adequate but not exceptional.

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

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

The description clearly states the verb 'Get' and the resource 'full details for a Federal Register document by its document number'. It distinguishes this tool from siblings like 'search_documents' by specifying the exact method of retrieval (document number), making the purpose unmistakable.

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

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

The description indicates when to use the tool (when you have a specific document number and need full details), providing clear context. However, it does not explicitly state when not to use it or mention alternative tools like 'search_documents' for cases without a document number, so it stops short of a perfect score.

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

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

Adds context beyond annotations by specifying the returned fields and the scoping to active subscriptions. 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?

Two sentences, front-loaded with purpose and return fields, then usage guidance. No unnecessary words.

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

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

For a simple tool with one optional parameter and no output schema, the description fully covers purpose, return, and usage. Annotations provide safety profile.

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 parameter description. The description mentions 'active' which aligns with the default behavior, but adds no extra detail beyond the schema.

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

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

The description clearly states it lists the caller's active subscriptions, specifies returned fields, and distinguishes from siblings like subscribe and unsubscribe.

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

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

Provides clear guidance on when to use this tool: to review existing subscriptions before adding more or to find an id to cancel. Implicitly contrasts with subscribe and unsubscribe.

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

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

Annotations are all false, but the description adds critical behavioral details: rate-limited to 5 per identifier per day, free and doesn't count against tool-call quota, team reads digests daily, and signal affects roadmap. No contradiction with annotations.

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

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

Single paragraph that efficiently covers purpose, usage guidelines, behavioral notes, and a constraint. Every sentence adds value with no redundancy. Front-loaded with the main 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?

Given the tool's simplicity (3 params, no output schema), the description covers purpose, usage, and behavioral constraints thoroughly. It does not describe post-submission feedback or confirmation, but that is not essential for selection/invocation.

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

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

Schema description coverage is 100%, so the schema already documents each parameter well. The description adds some context (e.g., not to paste prompts) but does not significantly enhance parameter understanding beyond the schema. Baseline of 3 is appropriate.

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

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

The description clearly states the tool's purpose: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It explicitly lists feedback types (bug, feature, data_gap, praise) and distinguishes from sibling tools by focusing solely on feedback submission.

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

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

Provides explicit when-to-use scenarios: wrong/stale data (bug), missing tool (feature/data_gap), praise. Also gives a negative instruction: 'don't paste the end-user's prompt.' Includes rate limits and quota info, offering comprehensive guidance.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds valuable context: data source (CF analytics-engine), privacy (no PII), schema of returned data (pack, tool, count), and caching behavior (5min-1h). This goes beyond annotations.

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

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

The description is concise yet complete, using a single paragraph with bullet-point-like structure. Every sentence adds value, no filler. The front-loading is effective: the first sentence states the core purpose.

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

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

Given the tool has one optional parameter, no output schema, and is simple read-only, the description fully covers what the agent needs: what it returns, use cases, data source, and caching. Annotations cover safety and idempotency. No gaps.

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

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

Schema coverage is 100% with an enum and description for the single parameter. The description adds semantic guidance: 'Shorter windows surface what's hot right now; longer windows show steady-state demand.' This helps the agent choose the appropriate window.

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 what the tool does: returns top tools, top packs, and total call volume over a recent window. The verb 'Returns' and specific resources ('top tools, top packs, total call volume') make the purpose unmistakable. It distinguishes from siblings like 'discover_tools' by focusing on aggregate usage 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 lists three use cases explicitly, helping an agent know when to invoke this tool. It does not explicitly mention when not to use it or alternatives, but the provided siblings list offers context for differentiation. The guidelines are clear and practical.

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, non-destructive), the description adds extensive behavioral context: scanning mechanisms, partition checks, Jaccard similarity filtering, placeholder filtering, fill check with live CLOB depth, and explicit warnings not to trade if realizable edge ≤ 0. 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 thorough and front-loaded with the core purpose, but it is relatively long. However, every sentence adds value given the tool's complexity, so it remains efficient without being wasteful.

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

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

The description fully explains return values (opportunities[], partition_check, fill_check), error conditions (skipped_low_similarity, placeholder filter), and edge cases. Without an output schema, it provides complete behavioral and output context.

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

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

The input schema covers both parameters with full descriptions, but the description adds substantial meaning—how each mode works (event walks child markets, topic cross-event scans), example usage, internal checks, and result components. This far exceeds the schema's basic definitions.

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

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

The description clearly states the tool finds arbitrage opportunities on Polymarket using monotonicity violations and partition-sum checks. It specifies the verb 'find', the resource 'arbitrage opportunities', and the mechanisms, distinguishing it from sibling tools like polymarket_edges and polymarket_fill_risk.

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

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

The description explicitly explains when to use no args (trending scan), event mode (single-event), or topic mode (cross-event). It recommends event mode for specific markets, describes limitations, warns about fill check conditions, and references polymarket_fill_risk for custom sizing, providing clear usage guidance.

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

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

Annotations indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, establishing safety. The description adds extensive behavioral context: model details (e.g., lognormal barrier from FRED, GDELT ratios), caching at KV level for 1h, diagnostic counters, and handling of Fed bets with explicit warning about unreliability without paid data. No contradiction with annotations.

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

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

The description is very detailed but somewhat verbose, including extensive model mechanics that could be condensed. It front-loads the main purpose and segments, but the middle sections (e.g., FIVE MODEL FAMILIES) add length without immediate clarity. A more structured format with bullet points would improve 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?

Despite no output schema, the description fully explains the response top-level fields (by_segment, fed_candidates, _diagnostics) and the structure within each segment (edge_pp_net, kelly_fraction, market info, 24h-move warning). It covers what callers need to interpret results and diagnose empty segments.

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 substantial meaning beyond parameter names and types. For example, it explains that min_liquidity should be set to 5000 to avoid walking the book, and that min_kelly skips opportunities too small to bet. Each parameter gets concrete rationale and use-case guidance.

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

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

The description clearly states it scans Polymarket markets for opportunities where Pipeworx data disagrees with market price, and specifies it's built for 'what should I bet on today.' It details three segments (model_driven, structural_arbitrage, concentrated_longshot) which distinguishes it from siblings like polymarket_arbitrage that likely cover different types of edge detection.

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

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

The description explains when to use the tool (discovering opportunities without paging) and provides tradeable-edge knobs (min_liquidity, max_spread_pp, etc.) and diagnostics to understand why segments are empty. However, it does not explicitly state when not to use this tool versus alternative siblings like polymarket_arbitrage or polymarket_edge_tracker, leaving some ambiguity.

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 that indicate it's read-only and idempotent, the description adds significant behavioral context: limits like 60-day snapshot TTL, decay computed from daily closes not intraday, and explanation of snapshot gaps. 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 a clear purpose sentence followed by explanation of response fields and limits. It is comprehensive but not overly verbose; each 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?

Without an output schema, the description fully compensates by detailing the response structure (tracked, expired, snapshot_dates) and their subfields (e.g., trend, decay_pp_per_day, lifespan_days). It also covers limitations, making it complete for an AI agent.

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

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

The schema covers 100% of parameters, but the description adds default values (14 for days, '1wk' for window) and bounds (max 30 for days), which are not in the schema. It also explains the window parameter's connection to polymarket_edges window families.

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 'track' and resource 'edge persistence and decay telemetry', clearly stating it answers how long an edge has existed and if it's shrinking. It distinguishes from sibling tools like polymarket_edges by focusing on temporal analysis.

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

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

The description provides clear context on when to use this tool (e.g., differentiating between a fresh wide edge and a 3-week-old wide edge), but does not explicitly state when not to use it or mention 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 confirm readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds valuable context about the internal calculations (top_of_book, vwap_fill_price, slippage_pp, verdicts) and warns about risks like thin books and unhedged positions. 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 well-structured with clear sections, bolded keywords, and front-loaded purpose. It is slightly verbose but every sentence adds value. Could be more concise, but organization is excellent.

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

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

Given the complexity of two modes and no output schema, the description thoroughly explains return fields for both modes, edge cases (thin legs, partial fills), and includes a verdict system. It covers most expected aspects, though error handling could be more explicit.

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%, giving baseline 3. The description enhances understanding by explaining how size_usd is interpreted differently in single-market vs basket modes, clarifying side defaults for basket, and detailing the use of market vs event parameters. 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 purpose as a realizable-vs-theoretical edge check against live order-book depth. It distinguishes between single-market and basket modes and explicitly positions itself relative to sibling tools like polymarket_arbitrage and 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 explicitly states when to use this tool (before acting on polymarket_arbitrage sell/buy-every-leg signals or polymarket_edges trades above $500) and explains why it's necessary (partial fills convert arb into directional risk). It also specifies required parameters (market or event) and defaults.

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

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

Annotations already declare readOnlyHint and destructiveHint false. The description goes beyond by detailing internal behaviors: compatibility_warning conditions (non-equivalent bet shapes, no token overlap), temporal_alignment flag, and counters for skipped comparisons. It also explains that spreads are mathematically meaningless when temporal alignment is false.

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

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

The description is thorough with well-labeled sections (TWO MODES, RESPONSE, SAFETY FIELDS) and front-loads the core purpose. It is slightly verbose but each sentence provides useful information given the tool's complexity.

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

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

Despite no output schema, the description explains the response structure (leg-by-leg prices, top_spreads_pp, safety fields) and covers edge cases (compatibility warnings, temporal alignment). It provides enough detail for an AI agent to invoke and interpret the tool correctly.

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

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

Schema coverage is 100%, and the description adds meaning: it explains the topic enum values, shows examples, and describes how explicit parameters override topic-mapped sides. This clarifies usage beyond the schema's property descriptions.

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

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

The description clearly states the tool computes the cross-venue spread between Kalshi and Polymarket for the same resolving question. It specifies the verb 'compute', the resource 'cross-venue spread', and distinguishes from siblings like polymarket_arbitrage by focusing on two-venue 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 explains two modes (topic shortcuts vs explicit tickers) and when each is appropriate. It warns that most pre-mapped topics yield compatibility warnings, guiding users to explicit mode for custom pairings. It does not explicitly exclude alternatives but provides sufficient context for when to use this tool.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds behavioral context about scoping to identifier and pairing with remember/forget, without contradicting annotations.

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

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

Three sentences front-loading the core function, then usage context, then pairing info. No redundant or irrelevant 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?

Lacks return format details, but the tool is simple (returns value or list). The description covers key behaviors and scoping. Could be more complete with output structure, but sufficient given context.

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

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

Schema coverage is 100% and the parameter description already states omitting key lists all keys. The description adds usage examples but does not provide additional semantic details 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 retrieves a value saved via 'remember' or lists all keys if key is omitted. It distinguishes from sibling tools 'remember' and 'forget' by specifying it is the retrieval 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 concrete examples of when to use (look up user's target ticker, address, research notes) and mentions scoping. Lacks explicit when-not-to-use or alternatives, but the context is clear.

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

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

Discloses key behaviors: mark_read flags events as read, polling is supported, and the same feed is available via GET endpoint. Aligns with annotations (readOnly, idempotent, not destructive) and adds 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?

Three succinct sentences that front-load the purpose, then detail filtering/behavior, and end with polling note and alternative. 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?

Covers return fields, filtering, mark_read, and polling. No output schema, but description sufficiently describes output shape. Could be more explicit about read-only nature, but annotations already indicate. Sufficient for agent decision-making.

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 meaningful context for type, since, and mark_read (e.g., example type 'sec_8k', ISO timestamp, and the read flagging effect). Does not add much for limit and unread_only, which are well-documented in schema.

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

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

The description clearly states the tool pulls fired events from a subscription feed, specifies the returned fields (source, citation_uri, raw payload), and distinguishes it from siblings like search_documents or get_document by focusing on subscription feed alerts.

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

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

Provides usage guidance on filtering by type and since, and explains the mark_read behavior for polling. Mentions an alternative API endpoint for scripts/dashboards. Lacks explicit exclusions or comparisons with sibling tools for 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, openWorldHint, idempotentHint, and destructiveHint. The description adds significant context: it fans out to multiple sources in one parallel call, describes fallback logic, notes PatentsView sunset, and details the return format (changes[] grouped by source, total_changes, pipeworx:// URIs). This provides rich behavioral insight beyond what annotations convey.

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

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

The description is relatively long but efficient—every sentence adds useful information. It is front-loaded with examples and structured logically. Could be slightly more compact, but overall well-organized.

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 covers return format (grouped changes, count, URIs), source behavior (fanned out), fallback logic, and parameter details. It is complete for the tool's complexity and context signals.

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 each parameter described. The description adds further value: it explains the since parameter accepts ISO date or relative shorthand with examples, and that value can be a ticker or CIK. This enriches the meaning beyond the schema alone.

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

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

The description starts with concrete user queries (e.g., "What's new with X", "latest on Y"), then defines the tool as a change feed for a company in a time window. It explicitly distinguishes from the sibling entity_profile tool, making the purpose clear and differentiated.

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

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

The description provides explicit examples of when to use the tool and specifically says to use entity_profile instead for static profiles. It also explains fallback behavior between GDELT and GNews, guiding the agent's decision-making.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint as safe. Description adds context about the data source (Federal Register), scope (every agency), and return fields (title, abstract, agency, effective dates, significance), which is valuable 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. Key information is front-loaded: purpose, scope, and differentiation from sibling tool. Efficiently structured.

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

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

For a simple tool with one parameter and an output schema, the description fully covers what the tool does, what it returns, and how it differs from siblings. No further information is needed for correct invocation.

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

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

The only parameter 'limit' is well-documented in the schema (default 20, max 100). Description does not add new param-level details but mentions the output fields, which indirectly helps. With 100% schema coverage, baseline is 3.

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

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

Clearly states the verb 'browse' and the specific resource 'most recently published final rules and regulations from the Federal Register'. Explicitly distinguishes from sibling tool 'search_documents' by noting the lack of topic filter.

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

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

Provides explicit guidance on when to use this tool (browsing general recent rules) and when to use the alternative 'search_documents' for specific topics. This helps the agent select the correct 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 indicate idempotent and non-destructive behavior. The description adds persistence details (24-hour retention for anonymous, scoped by identifier) that go beyond annotations.

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

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

The description is structured with purpose first, then usage, then technical details. Each sentence adds value; slightly longer but not wasteful.

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 write tool with no output schema, the description covers the main functional aspects, including retention and pairing with siblings. Missing return value info is acceptable given the tool's nature.

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 describes both parameters fully (key and value). The description doesn't add new parameter details beyond examples, so baseline 3 is appropriate.

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

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

The description clearly states the tool saves data for reuse, specifies the resource as a key-value store, and distinguishes it from sibling tools like recall and forget. It also mentions scope across sessions and authentication states.

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

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

It explicitly says when to use (discover something worth carrying forward) and pairs with recall/forget. While it doesn't list exclusions, the guidance is clear and contextual.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds that each call cascades through multiple lookup endpoints internally, replacing 2-3 manual lookups. 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 moderately long but well-structured, starting with example queries, then purpose, then usage, then type details. Every sentence adds value, though the nested details could be slightly more compact.

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 2 required params and no output schema, the description is fairly complete. It explains return values per type and the internal cascading behavior. Missing are error handling details or ambiguous input behavior, but overall it provides sufficient context.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds significant meaning beyond schema, detailing exactly what each entity type returns (e.g., for company: ticker, CIK, company_name, citation URI; for drug: RxCUI, ingredient, brand, citation).

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: resolving user-spoken names to canonical identifiers. It provides specific examples like 'What's the ticker for...' and details for each supported type (company, drug), explicitly distinguishing it from siblings by advising 'Use FIRST whenever you have a name but need an 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 gives explicit usage guidance: 'Use FIRST whenever you have a name but need an ID.' It explains the tool replaces manual lookups and provides examples of when to use it, though it does not explicitly state when not to use or list 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 (readOnly, idempotent, non-destructive) already provide transparency; description adds behavioral detail: internally calls ai_visibility_check, returns ranked list with score/confidence/signal density. No contradiction with annotations, and adds value beyond them.

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

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

Four sentences with clear front-loading of purpose. Could possibly tighten the second sentence but overall efficient and well-structured.

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

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

Given full schema coverage, rich annotations, and no output schema, description covers workflow, return shape (ranked list with fields), and intended use case. Lacks explicit output structure but still complete enough for an AI agent to interpret.

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 description adds key semantic context: 'first entry treated as the subject for narrative; rest are competitors', explains models and context parameters with nuance not in schema. Adds meaningful value beyond parameter names.

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

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

Description clearly states the tool compares AI visibility across multiple entities side-by-side, mentioning specific actions (probes each entity with ai_visibility_check, ranks by score) and distinguishing from siblings like ai_visibility_check (single) and compare_entities (generic).

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 gives a usage example ('does Claude know about us as well as our competitors?') but does not explicitly state when not to use or provide alternatives (e.g., using ai_visibility_check for single entity). Usage guidance is implied but not explicit.

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 'Partial failures degrade gracefully — bundlephobia's first measurement on a new version can take 5-30s; sources_failed will list it if it times out, the rest still returns.' This provides important behavioral context about timeout behavior and output structure beyond annotations. No contradiction.

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

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

Description is dense but well-structured, front-loading the main purpose. It is about 6 sentences covering purpose, usage, limitations, and return values. Every sentence adds value, though it could be slightly shortened without losing information. Still very good.

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 values: 'summary block (is_latest, license, published_at, advisory_count, bundle_kb_min, bundle_kb_gz, dependency_count, has_esm, tree_shakeable), per-advisory detail, links, and a list of recent alternative versions.' Also covers partial failures and ecosystem limits, making it complete for this multi-source tool.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds extra context: 'Scoped packages (e.g. @types/node) are accepted.' for package and 'Defaults to the latest published version when omitted.' for version. This adds value beyond the schema's minimal descriptions.

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

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

The description clearly states it's a composite check for npm packages, combining deps.dev and bundlephobia data. It specifies the verb 'check' and the resource 'npm package', and distinguishes from siblings by focusing on dependency analysis vs other tools like 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?

Explicitly says 'Use whenever an agent asks is X safe / popular / small or what does adding lodash cost me'. Also provides when-not: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly.' This gives clear guidance on when to use this tool vs alternatives.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable context about the relevance ranker returning decade-old documents for sparse-term queries without the 'since' parameter, and lists return fields. This adds 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?

The description is well-structured and front-loaded with the main purpose. It includes helpful examples and recommendations, though slightly verbose. Every sentence contributes value.

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

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

Given the tool's complexity, the description covers core functionality, differentiation from siblings, parameter recommendations, and output details. With an output schema present, it is complete enough for correct agent invocation.

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

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

Schema coverage is 100% so baseline is 3. The description adds value with examples and explains the 'since' parameter's effect and necessity, which goes beyond schema descriptions.

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

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

The description clearly states the tool searches the US Federal Register by topic/keyword for document types. It explicitly distinguishes itself from the sibling 'recent_rules' by noting that tool lacks a topic filter and returns unrelated results.

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

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

The description provides explicit usage guidance: 'Use this whenever the question mentions a SUBJECT'. It also advises against using recent_rules when topic filtering is needed and recommends using the 'since' parameter to avoid stale results.

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

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

Annotations already indicate safety (readOnly, idempotent). The description adds technical details: BGE-base-en embeddings, cosine similarity, 500-char windows, 200K char cap with truncation, and return fields (offsets, scores). This goes beyond what annotations provide and helps the agent understand 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?

Front-loaded with the core purpose. Two paragraphs, about 150 words, every sentence adds value. No redundancy. Well-structured for an agent to quickly grasp.

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

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

Despite no output schema, the description explains return format (top-N passages with offsets and scores) and the truncation behavior. It also connects to a sibling tool. Fully meets the needs for a complex tool.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the search mechanism (BGE, windows) and providing examples for the query parameter, helping interpretation beyond the schema's brief descriptions.

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

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

The description clearly states 'Semantic search INSIDE a fetched record' as the core action, with a specific verb and resource. It distinguishes from general search by specifying it operates on already-fetched text, but does not explicitly contrast with all siblings like search_documents, so not a perfect 5.

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

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

Explicitly says 'Use when the record is too big to cram into the prompt' and mentions pairing with ask_pipeworx_grounded, providing clear context for when to use. It lacks explicit 'when not to use' but the guidance is strong.

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

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

Annotations provide basic hints (readOnlyHint=false, destructiveHint=false), and the description adds valuable behavioral details: OAuth requirement, anonymous/BYO restrictions, delivery channel constraints (SMS cap, webhook signing, auto-disable), and the return of a subscription ID. The idempotentHint annotation might be inconsistent but is not directly contradicted.

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

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

The description is well-structured with clear sections for types and delivery channels, and front-loads the main purpose. It is somewhat lengthy but each sentence adds value; only minor tightening could be done.

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 with nested objects, multiple types), the description covers prerequisites (OAuth), type specifics with examples, delivery options with constraints, and the return value (subscription ID). No output schema exists, but the return is stated. It is fully adequate for an agent to use the tool correctly.

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

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

Schema coverage is 100%, but the description richly expands on each parameter with concrete examples (e.g., 'sec_8k: {ticker:"AAPL", items?:["5.02"]}'), clarifies nested objects for delivery and type-specific params, and explains webhook mechanics. This adds significant meaning beyond the schema.

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

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

The description clearly states the verb ('Create') and the resource ('proactive monitoring subscription to a live-data event stream'), and distinguishes this from sibling tools like 'unsubscribe' or 'list_subscriptions' by detailing the creation aspect.

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

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

The description provides explicit context for when to use this tool (monitoring, OAuth required) and lists supported types with examples. However, it does not directly compare with sibling tools like 'polymarket_edges' or mention when not to use it, leaving some room for improvement.

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

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the bar is lower. The description adds valuable context about returning example questions and being a live catalog, but 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 well-structured with front-loaded key points, uses examples and categories efficiently, and every sentence adds value with 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 simple tool (one optional param, no output schema), the description covers all necessary context: purpose, when to use, parameter effects, and expected output. It is fully complete for its level of complexity.

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

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

Schema coverage is 100%, but the description adds meaning by explaining the effect of omitting vs. providing the topic parameter ('full spread' vs. focused). This goes beyond the schema's basic description.

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

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

The description clearly states it is the onboarding entry point that returns category-bucketed example questions. It distinguishes itself from sibling meta-tools (e.g., ask_pipeworx, entity_profile) by specifying its role as the first tool to use when unfamiliar with Pipeworx.

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

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

The description explicitly says 'Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools,' providing clear guidance on when to use it and implicitly when to use alternatives.

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

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

Adds significant context beyond annotations: describes that the row is deactivated not deleted, historical events remain available, and ownership is enforced. No contradiction with annotations.

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

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

Two sentences, no filler, every sentence adds value. Front-loaded with purpose.

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

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

Simple tool with one parameter, no output schema, and annotations covering safety. Description fully explains behavior, constraints, and side effects.

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 for the single parameter 'id' with description. The description does not add extra parameter details beyond the schema, so baseline score applies.

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

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

The description states 'Cancel a subscription by id' clearly with a specific verb and resource, and it distinguishes from sibling tools like 'subscribe' and 'list_subscriptions'.

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

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

Provides explicit context about ownership enforcement and data handling (deactivation vs deletion), but does not explicitly contrast with alternatives like list_subscriptions or subscribe.

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

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

The description discloses behavioral traits beyond the annotations: it details the return structure (verdict types like confirmed, refuted, etc.), includes a citation source ('pipeworx://'), and mentions percent delta. It also notes that it v1 supports only company-financial claims. No contradiction with annotations; readOnlyHint and idempotentHint are consistent.

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

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

The description is fairly concise given the detail it provides. It opens with query patterns, then states usage, then specifics. It is well-structured and front-loaded. Could be slightly trimmed but it's 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?

Despite having only one parameter and no output schema, the description fully explains the tool's return values (verdict types, extracted structure, citation, delta) and limitations (v1 scope). It is complete enough for the AI agent to use correctly.

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

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

The single parameter 'claim' is already described in the input schema (100% coverage). The description adds value by providing examples of natural-language claims (e.g., 'Apple's FY2024 revenue was $400 billion'), which clarifies the expected input format and domain.

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: natural-language claim verification against authoritative sources. It provides specific examples ('Is it true that...', 'fact check') and specifies the domain (company-financial claims for US public companies). It distinguishes itself from sibling tools by stating 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 also clarifies the scope (company-financial claims) and provides example claims. While it doesn't explicitly list when not to use or alternatives, the context is clear enough for an AI agent.

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