Imf Portwatch

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

Annotations declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint false. The description adds significant details: probing multiple models, scoring, returning per-model fields (score, confidence, signals, raw_response), and the fee implication for Anthropic. 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?

Three sentences, front-loaded with purpose, then key details (default model, API key, return format). Every sentence adds value with no redundancy.

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

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

Given 4 parameters, 1 required, no output schema, the description covers inputs, output format, fee implications, and use cases. It is fully adequate for agent invocation.

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

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

Schema has 100% coverage for parameter descriptions. The description adds meaning: explains default model (workers-ai), that _apiKey is for Anthropic and involves direct payment, and that context disambiguates. Also describes the return structure.

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 probes LLMs about an entity and scores visibility 0-100 per model. It distinguishes from siblings like scan_competitor_ai_presence by specifying the scoring mechanism and supported models.

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 use cases (AI-marketing audits, pre-launch brand checks, competitive monitoring) and notes the default model is free while Anthropic requires a BYO key. It lacks explicit when-not-to-use but gives sufficient context.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint. Description adds that it returns structured answers with pipeworx:// citation URIs, routes to appropriate tool, and works on every tier. No contradictions; 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?

The description is long but front-loaded with the most important guidance (prefer over web search) and use cases. It packs valuable information but could be slightly more concise. Very informative 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?

Given no output schema, the description adequately explains return format (structured answer with citations). Covers input, use cases, alternatives, and operational context (works on all tiers, one fast call). Complete for the tool's complexity.

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

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

Schema coverage is 100% with all parameters described. The description mentions aliases and gives examples, but does not add deeper meaning beyond what the schema already provides. Meets baseline for high coverage.

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

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

The description clearly states the tool routes questions to a vast set of 4,396 tools across 1,102 sources, covering many domains. It distinguishes from siblings like ask_pipeworx_grounded and deep_research, making its purpose and differentiation explicit.

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

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

Provides explicit guidance: 'PREFER OVER WEB SEARCH', lists concrete examples, specifies when to use (factual questions like 'what is', 'look up'), and tells when to step up to alternatives (ask_pipeworx_grounded for hallucination-resistant answers, deep_research for broad questions).

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 significant value by detailing the internal routing logic, extraction-only policy, explicit refusal reasons, and the extra LLM call cost. 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 front-loaded with the core purpose, then explains routing, output structure, use cases, and cost trade-off. Every sentence adds unique value; no fluff. Efficiently packed without being overly long.

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 (routing across 4,396 tools) and lack of output schema, the description thoroughly covers the return structure (answer, evidence, confidence, source, fetched_at, refusal_reason), refusal scenarios, and when to use. Combined with annotations and schema, the context is fully sufficient 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?

Schema coverage is 100% with descriptions for all 6 parameters (all aliases for the question). The description does not add parameter-level semantics beyond what the schema provides. Baseline of 3 is appropriate as the schema already documents parameters fully.

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 is a hallucination-resistant answer mode for high-stakes reads, differentiating it from ask_pipeworx by emphasizing that it extracts answers solely from tool results and refuses when data cannot directly answer. It lists specific use cases (financial verdicts, legal claims, medical lookups, public statements), making purpose highly precise.

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

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

Explicitly instructs to use when answers will be quoted, cited, or acted upon, and advises preferring ask_pipeworx for casual lookups. Highlights the cost of an extra LLM call, providing clear context for when to choose this tool over its sibling.

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

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

Annotations (readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false) indicate a safe, read-only, idempotent tool. The description adds extensive behavioral details: low-confidence resolutions short-circuit with status, closed markets return status, wide spreads carry tradeability note, resolution-rule risk (cancellation rule), and response shapes for various fields. No contradictions with annotations.

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

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

The description is long and detailed, organized into sections (CLASSIFIERS, FAN-OUT EXAMPLES, RESPONSE SHAPES, etc.). While structured and informative, it could be more concise. The front-loading of the main purpose is good, but the length may overwhelm.

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

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

Given the complexity of the tool (3 parameters, no output schema but detailed description), the description is highly complete. It covers input formats, fan-out logic, response structure (including edge cases like low-confidence matches, closed markets, wide spreads, cancellation rules), and safety mechanisms. Every important aspect seems addressed.

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 significant meaning beyond the schema: it explains how 'market' can be a slug, URL, or question text, provides examples, and elaborates on the 'depth' and 'include_raw' parameters with usage notes. This adds context that helps the agent understand parameter semantics.

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

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

The description clearly states the tool's purpose: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It specifies input types (slug, URL, question text) and the overall workflow (resolve, classify, fan-out, return evidence packet + comparison). It distinguishes from siblings like polymarket_edges and polymarket_arbitrage, which focus on edge calculation or arbitrage, respectively.

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

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

The description explicitly states when to use: 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z".' It provides fan-out examples by category, giving clear context. However, it does not explicitly mention when not to use or suggest alternative tools, missing a small opportunity for clearer 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 declare readOnly, idempotent. Description adds behavioral details beyond annotations: 'Returns time series ordered most-recent-first, with per-cargo-type breakdown', and 'Accepts friendly names or portid'. No contradictions.

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

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

Two sentences: first defines output, second adds usage context and input details. Every sentence contributes purpose and guidance. No redundant or vague phrasing.

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 parameters and no output schema, description explains return format (time series, order, breakdown) and input variants. Could mention response structure more explicitly (e.g., fields), but sufficient for a straightforward data 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 covers both parameters (100% coverage). Description adds value by listing accepted friendly names ('suez / panama / hormuz / bab-el-mandeb / etc.') and specifying lookback defaults (30) and max (365), though the latter is in schema. The example list enhances usability beyond schema descriptions.

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

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

The description clearly states it returns 'Daily vessel counts and aggregate capacity... transiting a specific chokepoint' and provides concrete use cases like 'is Suez traffic back to normal'. It distinguishes from siblings (e.g., chokepoints_list) by focusing on time-series traffic 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?

Explicit usage scenarios are given ('Use for ... any bet predicated on a chokepoint disruption persisting') and examples of valid inputs (friendly names, port IDs). No explicit when-not-to-use, but context strongly implies it's for traffic analysis, not listing chokepoints (handled by sibling).

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the description doesn't need to restate safety. It adds value by specifying the exact set of chokepoints and data included, which is behavioral detail 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 extremely concise: two sentences that immediately convey purpose, content, and usage distinction. Every word adds value with no redundancy.

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

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

For a zero-parameter, read-only tool with no output schema, the description fully documents what data is returned (8 chokepoints, annual counts, traffic mix, top industries). The annotations cover behavioral safety, making the description 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?

The tool has zero parameters, and the input schema is fully covered (100%). The description adds no parameter information because none is needed, and it fully explains what the tool returns, effectively compensating for the lack of output schema.

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

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

The description clearly states the tool lists the 8 major maritime chokepoints with specific data (annual vessel counts, traffic mix, top industries). It uses a specific verb 'List' and explicitly distinguishes from sibling 'chokepoint_daily_traffic' for live data.

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

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

The description provides explicit guidance: 'Use to discover what a chokepoint normally carries — for live daily throughput call chokepoint_daily_traffic.' This clearly states when to use this tool and when to use an alternative.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds: data sources (SEC EDGAR, FAERS), sorting by primary metric, citation URIs, and efficiency claim (replaces 8–15 lookups). No contradictions.

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

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

Description is dense but well-structured: query shorthand, key behavior, then type-specific details, sorting, citations, efficiency claim. Every sentence adds value with no redundancy.

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

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

No output schema, so description explains returned data per type (revenue, net income, cash, debt, adverse event counts, trial counts) and mentions citation URIs. Covers off-calendar fiscal year handling. Complete for a comparative tool.

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

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

Schema coverage is 100%, but description adds context: for 'type' explains differences between company and drug data; for 'values' gives example formats (tickers vs drug names) and count constraints (2-5). Enhances beyond schema.

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

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

The description starts with clear query examples and states: 'side-by-side comparison of 2–5 companies or drugs in ONE parallel call.' It specifies verb ('compare') and resource ('entities'), and distinguishes from siblings like entity_profile by emphasizing parallel comparison.

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

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

Explicitly says 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' Provides concrete examples of queries and explains what each entity type (company vs drug) returns. Also notes correct handling of off-calendar fiscal years.

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 readOnlyHint, openWorldHint, idempotentHint. Description adds account requirements, paid plan for 'thorough', parallel decomposition, return format (findings packet with gaps[]), timing (15-60s), and limitation (empty gaps for non-structured topics). 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?

Single paragraph, front-loaded with key constraints (account required, not open-web). Slightly long but every sentence adds value; could be broken into sections but remains clear.

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

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

No output schema, but description fully explains return format: findings packet with evidence, confidence, source, fetched_at, citation, and explicit gaps[]. Also covers prerequisites, timing, and failure mode.

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. Description adds context: depth enum translates to facet counts (quick=3, standard=5, thorough=8) and notes default. Question parameter explained as natural language, broad/multi-part fine.

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 'Grounded multi-source research across Pipeworx's 1102 STRUCTURED data sources' in one call, with explicit contrast to siblings like ask_pipeworx. Verb+resource is specific and distinguishable.

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 when to use (broad/multi-part structured data questions) and when not to (breaking news, open-web topics). Names alternative tools (ask_pipeworx) and explains their different use cases.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds behavioral context beyond annotations: it explains that results come with full input schemas and curated examples, ready to call directly without a second lookup. While it doesn't detail error handling or parameter limits (beyond what's in the schema), the added value justifies a 4.

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 at two sentences. The first sentence clearly states the core function, and the second elaborates on usage and output. Every sentence contributes meaning, and the structure front-loads the most critical 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?

Despite no output schema, the description fully explains the return value: 'top-N most relevant tools with names, descriptions, and full input schemas (with curated examples).' It also covers parameter defaults (limit default 20, max 50) via the schema. The description is complete given the tool's complexity and the richness of annotations.

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

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

Schema description coverage is 100%, so the schema already documents all parameters. The description adds value by explicitly listing aliases for the query parameter (task, q, description, search) and providing example queries, which reinforces parameter semantics without introducing new information 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: 'Find tools by describing the data or task.' It specifies the return format (top-N tools with names, descriptions, and schemas) and distinct use cases (SEC filings, financials, etc.), effectively differentiating it from sibling tools like deep_research or ask_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 provides explicit when-to-use guidance: 'Use when you need to browse, search, look up, or discover what tools exist.' It also advises 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This clearly communicates its role as an exploration tool, distinguishing it from direct answer tools.

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

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

Discloses fans out across multiple sources, soft-fails for patents (USPTO sunset), and return fields. Annotations (readOnlyHint, idempotentHint) are consistent; description adds behavioral details beyond annotations.

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

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

Description is informative but slightly verbose; front-loaded with examples. Every sentence adds value, but could be tightened without sacrificing clarity.

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

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

With 100% schema coverage and no output schema, description fully explains return fields (CIK, filings, fundamentals, patents, news, LEI) and limitations. Complete for a holistic profile tool.

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

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

Schema coverage is 100% and description adds meaning: 'type' enum only 'company', 'value' ticker or CIK, names not supported. Provides context not in schema alone.

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

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

Description clearly states it returns a full cross-source profile of a US public company. Multiple example queries ('Tell me about X', 'brief me on Tesla') illustrate the tool's purpose. Distinguishes from chaining individual lookups.

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

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

Explicitly says 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups' and instructs to use resolve_entity for names. Clearly signals when to use and what alternatives exist.

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?

Aligns with annotations (destructiveHint=true, idempotentHint=true). Description adds no contradictions but no extra behavioral details 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 efficient sentences front-loaded with action, usage, and related tools. 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?

Complete for a simple deletion tool with annotations; describes purpose, usage, and parameter sufficiently.

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 100% with description 'Memory key to delete'. Description adds no further parameter meaning beyond 'by key'.

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?

Explicitly states 'Delete a previously stored memory by key' with clear verb and resource. Distinguishes from siblings by pairing with 'remember' and 'recall'.

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

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

Provides explicit when-to-use scenarios: stale context, task completion, clearing sensitive data. Also mentions related tools for context.

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

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

Annotations already indicate a safe, read-only, idempotent operation. The description adds value by explaining the process ('Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format') and the output format, which is beyond the annotations.

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

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

The description is two well-structured sentences plus a list of use cases. It front-loads the main purpose and contains no superfluous 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?

For a tool with two simple parameters and no output schema, the description adequately explains the output format ('single text blob ready to drop at site-root/llms.txt') and the process, making it complete.

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

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

Schema coverage is 100% with clear parameter descriptions. The tool description reinforces the process but doesn't add new semantic details 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 the action (generate), the resource (llms.txt file), and the context (for any URL for AI crawlers). It distinguishes itself from siblings like 'ai_visibility_check' by focusing specifically on generating a standardized file.

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 ('getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor'), but does not mention when not to use it or compare to alternatives.

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

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

The annotations already declare readOnlyHint, idempotentHint, and non-destructive. The description adds value by detailing the specific fields returned and the default of active-only, which is beyond the annotation scope.

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 cover purpose, return fields, and usage advice 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?

For a simple list tool with one optional parameter and strong annotations, the description provides sufficient context about return and usage, though not exhaustive.

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 'include_inactive' is well-described in the schema. The description reinforces the default behavior but doesn't add significant new meaning beyond that.

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 'List the caller's active subscriptions' with a specific verb and resource, and lists the return fields. It distinguishes from siblings like subscribe/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 explicit context: 'Use this to review what you're monitoring before adding more or to find an id to cancel.' This guides the agent on when to use it, though it doesn't explicitly state when not to use.

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

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

The description adds behavioral context beyond annotations: it is rate-limited (5 per day), free, and does not count against tool-call quota. It also explains that the team reads digests daily and feedback affects roadmap. Annotations are sparse, so this adds useful transparency.

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

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

The description is moderately sized and well-structured, front-loading the purpose and usage. Every sentence adds value, though a minor redundancy exists ('describe the issue in terms of Pipeworx tools/packs' repeats earlier examples). Overall, clear and 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?

For a simple feedback tool with 3 parameters and no output schema, the description covers all essential context: what to include in the message, how to structure the context, rate limits, and impact. It leaves no ambiguity for the agent.

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

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

Schema coverage is 100%, but the description elaborates on the 'type' enum and advises on message content (be specific, mention tool/pack). It adds nuance to the 'context' parameter by listing typical fields (pack, tool, vertical) and reinforces acceptable feedback topics.

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 the tool sends feedback to the Pipeworx team for bugs, missing features, or praise. It lists specific use cases (bug, feature, data_gap, praise) and clearly distinguishes itself from sibling tools like data retrieval or 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?

The description explicitly provides when to use the tool (for bugs, missing tools, praise) and when not to (e.g., not to paste end-user prompts). It also mentions rate limits and quota-free usage, giving clear guidance for agent 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 indicate read-only, idempotent, open-world, and non-destructive. The description adds valuable context: source (CF analytics-engine), no PII, caching behavior (5min-1h), and aggregate format. No contradictions.

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

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

The description is concise (4 sentences, including bullet-like use cases) and well-structured: first sentence states what it does, then reasons to use it, then technical details. 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?

For a simple tool with one parameter, no output schema, and clear annotations, the description fully covers return values (top tools, packs, count), caching, and data source. No gaps remain.

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%. The description augments the schema by explaining the semantics of different windows (hot vs steady-state demand), adding value beyond the enum labels.

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

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

The description clearly states the tool returns top tools, top packs, and total call volume over recent windows. It provides three explicit use cases, distinguishing it from sibling tools like ask_pipeworx or discover_tools.

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

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

The description provides three specific usage scenarios (discovering hot data sources, confirming popular tools, aligning use cases). While it doesn't list explicit exclusions or alternatives, the context makes it clear this is for trending data, not for general queries.

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

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

Annotations declare readOnlyHint=true, consistent with analysis tool. Description adds extensive behavioral details: walks child markets, checks ordering, computes partition_check, semantic anchor with Jaccard similarity, partition filter, and fill check against live CLOB depth. No contradictions.

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

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

Well-structured with sections (REQUIRES, SEMANTIC ANCHOR, etc.) but slightly verbose. Every sentence adds value, but could be tightened with bullet points for easier parsing.

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

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

Describes all aspects: input requirements, processing details, response structure (opportunities, partition_check, fill check), and cross-references sibling tool. Even without output schema, explanation suffices.

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 value: explains what slugs look like, what seed questions are appropriate, and the distinct modes each parameter triggers. Goes far 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?

Clearly states it finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. Distinguishes between event (single-event mode) and topic (cross-event mode) with examples. Differentiates from sibling tools like 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?

Explicitly requires one of event or topic, warns that call with no args fails. Recommends event for a specific market, topic for cross-event scanning. Provides examples and tells when to use sibling tool for custom sizing.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description goes far beyond by detailing edge calculation (net of slippage), segment logic (model_driven, structural_arbitrage, concentrated_longshot), inclusion/exclusion rules (placeholder-slug filter, Fed bet exclusion), and caching behavior (1h at KV level). No contradictions with annotations.

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

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

The description is lengthy and dense with technical detail. While it is front-loaded with the core purpose, the later sections containing segmentation logic and parameter explanations could be more concise. Every sentence adds value, but the overall verbosity may hinder quick comprehension.

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

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

Given the tool's complexity (9 parameters, no output schema, nested response structure), the description thoroughly covers inputs, behavior, output format (by_segment with diagnostics), caching, and edge-case handling (empty segments, Fed exclusion). It provides sufficient context for correct invocation without needing external documentation.

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

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

Schema coverage is 100% with descriptions for all 9 parameters. The description adds meaningful context beyond the schema, such as explaining 'tradeable-edge knobs' (min_liquidity, max_spread_pp) and the per-leg Kelly filter (min_partition_leg_kelly). This enhances understanding of how parameters affect output.

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

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

The description clearly states the tool scans Polymarket markets for opportunities where Pipeworx data disagrees with market price. It specifies the output is opportunities with edge metrics. However, it does not explicitly differentiate from sibling tools like polymarket_arbitrage or polymarket_edge_tracker, though the unique three-segment approach provides implicit distinction.

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

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

The description includes 'Built for "what should I bet on today"' which indicates usage context. It mentions agents can discover opportunities without paging hundreds of markets. However, it does not specify when not to use this tool or mention alternatives explicitly, leaving the agent to infer from sibling tool names.

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

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

Annotations already declare readOnly, openWorld, idempotent, non-destructive. The description adds substantial context: return structure (tracked, expired, snapshot_dates), explanations of fields (trend, decay_pp_per_day), data freshness (triggered by cache-miss), and limitations (60-day TTL, daily closes). 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 lengthy but each sentence adds value. It front-loads the core purpose, then details arguments and response fields. Slight redundancy in the limits section could be tightened, but overall well-structured.

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

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

With no output schema, the description fully documents the return value structure including fields, data types, and meaning. It also covers limitations and data freshness. The tool is fully self-contained.

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 default values and clamp ranges. Description reinforces defaults and explains the 'window' parameter as 'snapshot family', adding semantic context beyond the schema's description.

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

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

The description states the tool provides 'edge persistence and decay telemetry' from daily snapshots, answering specific questions about edge longevity and trend. It clearly distinguishes from sibling 'polymarket_edges' by focusing on temporal tracking rather than raw snapshots.

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 this tool (for persistence/decay info) with an example contrasting fresh vs old edges. It does not explicitly exclude use cases or point to alternatives, but the context is clear enough.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=true, implying no side effects. The description adds that it 'walks the ladder' and returns fill details. It could mention it does not execute trades, but the verdict system implies a simulation. No contradiction; good extra 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 well-structured with section headers (SINGLE-MARKET, BASKET) and lists outputs. It is front-loaded with purpose. Though somewhat verbose, every sentence adds value. Minor reduction could 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?

Given no output schema, the description fully documents outputs (top_of_book, vwap_fill_price, etc.) and their meaning. It covers edge cases: thin_legs, forced_directional_risk, partial fills. Tells the agent how to interpret results (verdict, max_clean_notional_usd). Highly complete.

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

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

Schema coverage is 100% (all 4 parameters described). The description adds meaning: explains size_usd in each mode, side defaults (auto for basket), mutual exclusivity of market/event, and clamp range. This 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 performs a 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It distinguishes between single-market and basket modes, lists specific outputs (top_of_book, vwap_fill_price, etc.), and explains the verdict system. This specificity separates it from siblings 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?

Explicitly states 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It explains why: theoretical overround on thin books is not capturable, and partial basket fills create unhedged directional risk. This provides clear when-to-use and why-not-to-skip.

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 extensively discloses behavioral traits beyond annotations: it explains the compatibility_warning in two cases (shape mismatch and semantic mismatch), temporal_alignment flag, and skipped_cross_type counters. It also notes that spreads are mathematically meaningless when temporal alignment is false. This provides crucial context that annotations alone do not cover.

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

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

The description is well-structured, starting with the core purpose, then detailing modes, response fields, and safety warnings. It is dense but every sentence adds value. Minor improvement could be breaking into sections, but current structure is effective.

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

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

Despite no output schema, the description fully explains the response fields (leg-by-leg prices, top_spreads_pp, compatibility_warning, temporal_alignment, skipped counters). It also covers edge cases and limitations, making it complete for an AI agent to decide when and how to use the tool.

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

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

With 100% schema coverage, the baseline is 3. The description adds value by explaining the two modes (topic vs explicit) and how parameters interact: topic auto-fetches matching events, while explicit tickers override the topic-mapped side. This goes beyond the schema's property descriptions.

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

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

The description clearly states it computes the cross-venue spread between Polymarket and Kalshi for the same resolving question. It distinguishes itself from sibling tools like polymarket_arbitrage by focusing on cross-venue comparison and explaining two modes of operation.

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 the tool (for cross-venue spreads) and explains the two modes (topic shortcuts vs explicit tickers). It also warns that most pre-mapped topics currently return compatibility warnings, setting expectations. However, it does not explicitly compare to alternative tools like polymarket_arbitrage.

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. The description adds that the tool returns specific fields, but does not disclose new behavioral traits beyond what annotations provide. 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?

Two sentences: first sentence defines purpose and scope, second sentence lists outputs and use cases. Every word adds value, no redundancy.

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

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

For a search tool with 3 optional parameters and no output schema, the description fully explains inputs, outputs (including vessel counts, industries, trade share), database size, and sample use cases. 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 description coverage is 100% (all three parameters documented). The description adds minor context (e.g., mentioning LOCODE/portid output), but does not significantly enhance understanding beyond the schema. Baseline 3 is appropriate.

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

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

The description explicitly states the tool searches a port database by name, country, or ISO3, and lists the returned fields. It clearly distinguishes itself from sibling tools like chokepoint tools or entity_profile.

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 usage contexts: identifying ports affected by country-level disruption or finding LOCODE/portid. While no explicit when-not-to-use or alternatives, the sibling list shows no overlapping tool, so guidance is sufficient.

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

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

Annotations already declare read-only and idempotent; description adds scope (scoped to identifier) and pairing relationships, adding useful context beyond annotations.

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

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

Three sentences, front-loaded with purpose, 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?

Complete for a simple read tool with comprehensive annotations; covers purpose, usage, scope, and sibling relations.

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 schema description already explains the parameter well; tool description adds minimal extra meaning for the parameter itself.

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

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

Clearly states the tool retrieves values saved via remember or lists all keys, with specific verb and resource. Differentiates from siblings like remember and forget.

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

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

Provides clear context for use (look up stored context without re-deriving) but lacks explicit when-not-to-use instructions.

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 behavioral traits beyond annotations: describes return fields (source, citation_uri), filtering options, and state-modifying effect of mark_read. Consistent with readOnlyHint and destructiveHint. Provides rich context for agent understanding.

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

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

Concise four sentences, front-loaded with primary purpose. Every sentence adds value without verbosity.

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

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

For a tool with no output schema, description covers return content, filtering, state change, and alternative access. Adequately complete given moderate complexity of 5 optional parameters.

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 good descriptions. Description adds extra context like mark_read affecting subsequent calls, which enhances understanding 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?

Clear verb 'Pull' and specific resource 'fired events from your subscription feed'. Distinguishes from sibling tools like list_subscriptions and recall by focusing on alerts/events.

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 mentions polling is fine and provides an alternative access method (GET registry.pipeworx.io/alerts.json). Gives usage context but does not explicitly state when not to use it compared to siblings.

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

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

Beyond annotations (readOnlyHint, idempotentHint, etc.), the description discloses fallback behavior (GDELT→GNews on rate limits), USPTO soft-fail, and return format (changes grouped by source, total count, citation URIs). No contradictions with annotations.

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

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

The description is a single paragraph packing a lot of information, but it could be better organized (e.g., bullet points for sources). It is front-loaded with example queries, making it quick to understand.

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

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

Given no output schema, the description explains the return structure (changes[] grouped by source, total_changes count, pipeworx:// URIs). It also covers fallback and soft-fail scenarios, making it fully self-contained for this complex 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%, but the description adds practical examples for 'since' (ISO date, relative shorthand like '7d', '30d') and typical usage. It also explains 'value' can be ticker or CIK. 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 it is a change feed for a company, listing multiple example queries and specifying it fans out to SEC EDGAR, GDELT/GNews, and USPTO. It distinguishes itself from the sibling entity_profile by explicitly noting when to use that tool instead.

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

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

The description provides explicit when-to-use examples like 'What's new with X' and 'latest on Y', advises against using it when static profile is needed (pointing to entity_profile), and gives practical guidance on the 'since' parameter (e.g., 'Use 30d or 1m for typical monitoring').

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. Description adds context about data sources (PortWatch) and event types, which is consistent and complementary.

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

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

Two sentences with no filler: first sentence defines what the tool returns, second sentence gives use cases. Perfectly front-loaded and 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?

With no output schema and four optional parameters, the description adequately explains the tool's capabilities and return data. Provides enough information for an agent to decide when to invoke it.

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?

All four parameters have schema descriptions, and the description adds usage examples and filtering guidance (e.g., 'Filter by country, alert level, or year'), enhancing meaning beyond the schema.

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

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

The description clearly states the tool retrieves port-affecting disruption events from PortWatch, listing specific event types and data fields. It distinguishes itself from siblings like 'recent_alerts' by focusing on disruptions with severity and impact metrics.

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 example queries for common use cases (e.g., 'what disrupted shipping in the last month'). Does not explicitly mention when not to use or list alternatives, but the examples strongly imply appropriate contexts.

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 scoping by identifier, persistent vs. temporary memory (24 hours for anonymous), and idempotent nature. Annotations only hint at idempotency; description adds critical 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?

Three well-structured sentences, front-loaded with purpose, no redundant information. Efficient and readable.

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

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

Covers all necessary aspects: purpose, usage, scoping, persistence, and pairing with siblings. No output schema needed for a write operation.

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

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

Schema coverage is 100% with clear descriptions. Description adds illustrative examples for key formats and value types, enhancing usability beyond schema.

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

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

The description clearly states the tool saves data for reuse later as key-value pairs. It distinguishes from siblings like recall and forget, explicitly named.

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

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

Provides explicit when-to-use guidance: when discovering information worth carrying forward. Pairs with recall and forget. Lacks explicit 'when not to use' but context is sufficient.

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

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

Beyond the annotations (readOnlyHint, etc.), the description adds valuable behavioral context: it cascades through multiple lookup endpoints internally, replaces 2-3 manual lookups, and details exactly what each type returns (e.g., ticker + CIK + company_name for company, with citation URI).

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

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

The description is slightly long but well-structured, starting with user-facing example queries and then detailing supported types. Each sentence adds value, though it could be tightened while preserving clarity.

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

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

Despite having no output schema, the description comprehensively covers return values for each entity type, including citation URIs. It fully equips an agent to use the tool correctly without needing external documentation.

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

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

Even though schema coverage is 100%, the description adds meaningful examples (e.g., for value: "ticker (AAPL), CIK (0000320193), or name") and clarifies acceptable input formats for each type. This significantly aids correct parameter usage.

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

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

The description uses specific verbs and examples ("resolve a user-spoken NAME to the canonical/official identifier") and lists supported entity types with concrete use cases ("What's the ticker for…"). It clearly distinguishes its role as a prerequisite for other tools that require IDs.

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

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

Explicit guidance to "Use FIRST whenever you have a name but need an ID." Also explains that using resolve_entity replaces multiple manual lookups. However, it does not explicitly state when not to use it or mention alternative tools among siblings.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds that it probes each entity using ai_visibility_check and ranks results, providing useful internal behavior 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 sentences: purpose, process, use case. Every sentence adds value, no fluff. Well-structured and front-loaded.

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

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

Given complexity and no output schema, the description explains return values (ranked list with score, confidence, signal density). Could mention rate limits or multiple calls, but overall complete.

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

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

Schema description coverage is 100%. The description adds semantic meaning: explains entities ordering (first as subject), default for models, and clarifies context usage. No gaps remain.

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

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

The description uses a specific verb-resource pair ('Compare AI visibility across multiple entities side-by-side') and clearly distinguishes from sibling tools like ai_visibility_check (single entity) and compare_entities (generic 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 gives an explicit use case ('competitive AI-marketing audits') and implies when not to use (single entity checks). It lacks explicit exclusion of alternatives but provides clear context.

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

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

Beyond annotations (readOnlyHint, idempotentHint, etc.), the description discloses partial failure behavior—bundlephobia's first measurement can take 5-30s, and sources_failed will indicate timeouts while other data returns. No contradiction with annotations.

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

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

The description is a single dense sentence that front-loads the core purpose ('Composite check in ONE call'), then efficiently lists the sources and return structure. Every part adds value without redundancy.

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

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

Despite no output schema, the description enumerates all return components (summary block fields, per-advisory details, links, alternative versions), covers fallback guidance, and explains partial failure. This ensures an agent understands what to expect fully.

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: scoped packages are accepted for 'package', and 'version' defaults to latest when omitted. This enriches the schema information effectively.

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

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

The description explicitly states the tool is a composite check for deciding whether to add an npm package, specifying the sources (deps.dev, bundlephobia) and the question it answers. This clearly distinguishes it from sibling tools like 'scan_competitor_ai_presence' or 'validate_claim', which serve different purposes.

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

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

The description provides explicit use cases ('is X safe / popular / small', 'what does adding lodash cost me'), along with ecosystem limitations (NPM only in v1, with alternatives noted for other ecosystems). This gives clear guidance on when to use and when to fall back to other tools.

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

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

Adds value beyond annotations: details embeddings model (BGE-base-en), window size (500-char overlapping), char cap (200K), truncation flagging, output includes offsets and similarity scores. No contradiction with annotations.

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

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

Three sentences, front-loaded key info, no wasted words. Well-structured and easy to parse.

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

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

Given 3 parameters, no output schema, description covers usage, behavior, parameter details, and output expectations (offsets, scores). Complete enough for reliable tool 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% with descriptions. The description adds context like natural-language query examples and mentions top-N passages for limit, enriching understanding beyond schema.

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

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

The description clearly states it performs semantic search inside a fetched record, with specific examples (SEC 10-K, article). It distinguishes from siblings by mentioning pairing with ask_pipeworx_grounded and the fetch workflow.

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 prompt, and pairs with ask_pipeworx_grounded. No explicit when-not, but context is clear enough.

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

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

Annotations provide idempotentHint=true but description implies a new resource is created each time, creating ambiguity. Description discloses auth needs (OAuth), delivery channel limitations (SMS cap, phone verification, webhook auto-disable), but lacks clarity on idempotency 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?

Description is somewhat lengthy but well-structured with bullet points for types and delivery channels. It front-loads the main purpose and return. Every sentence adds value, though could be slightly more streamlined.

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

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

Given 3 parameters, 100% schema coverage, no output schema, the description covers the return (subscription id), delivery channels, and always-on feed. It provides sufficient context 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?

Description adds extensive meaning beyond the input schema with concrete examples for each type, parameter constraints, and delivery channel specifics (e.g., phone verification, webhook secret once, 10/day SMS cap). Schema coverage is 100% and examples are detailed.

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 creates a proactive monitoring subscription to a live-data event stream, identifies the return (subscription id), and distinguishes from siblings like list_subscriptions and unsubscribe by focusing on creation.

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

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

The description explains when to use (create subscription) and includes prerequisites (OAuth account, phone verification for SMS, webhook details), but does not explicitly state when not to use or compare with alternative tools for listing or deleting subscriptions.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. Description adds behavioral context: output is drawn from a live catalog, returns exact tool+argument shapes, and explains topic usage. No contradiction.

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

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

Front-loaded with aliases and purpose. Structured with dashes and clauses. Slightly lengthy but each sentence provides value; could be tightened.

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

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

No output schema, but description fully explains return structure (categories of example questions, tool+argument shapes). Covers optionality, order of use, and integration with meta-tools. Complete for an onboarding tool.

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

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

Schema coverage is 100%, baseline 3. Description adds value by listing example topics (finance, pharma, etc.) and explaining that omitting topic gives a full cross-category spread, going beyond the schema.

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

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

Description clearly states the tool is the onboarding entry point returning category-bucketed example questions. It uses specific language like 'Returns category-bucketed example questions' and distinguishes from siblings by being the generic 'what can I ask' tool.

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

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

Explicitly instructs 'Use this FIRST when you do not yet know what Pipeworx can do for you' and specifies when to pass topic vs. no arguments. Sibling tools are specialized, providing clear alternatives.

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

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

The description explains that the row is deactivated (not deleted) and that historical events remain available via recent_alerts, adding behavioral context beyond annotations.

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

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

Two sentences, front-loaded with purpose, and efficient 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 single parameter and no output schema, the description fully explains the action and its effects, including ownership and deactivation behavior.

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

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

Schema coverage is 100%, and the description does not add additional meaning to the 'id' parameter beyond what the schema provides. 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 states 'Cancel a subscription by id,' clearly specifying the verb and resource. 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?

Ownership enforcement is mentioned, guiding use to only own subscriptions. However, no explicit when-not-to-use or alternative tools are provided beyond the immediate context.

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

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

Description adds behavioral context (verdict types, structured output, citation, delta) beyond annotations that already declare readOnlyHint, idempotentHint, etc. No contradictions; provides useful details about data sources and return format.

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

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

Description is concise and front-loaded with purpose and usage. While a single dense paragraph, 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?

Despite lacking output schema, description fully explains the return value (verdict, structured form, actual value, citation, delta) and supported scope (company-financial claims via SEC EDGAR + XBRL). Complete for 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?

Single parameter 'claim' with 100% schema coverage. Description adds example claims and explains natural-language format and domain, significantly enhancing agent understanding beyond the schema.

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

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

Description clearly states the tool's purpose: natural-language claim verification for company-financial claims, with specific verb phrases and examples. It distinguishes from sibling tools like bet_research or deep_research by specifying domain and data sources.

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

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

Explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct' and explains efficiency gains over sequential calls. Does not exhaustively list when not to use, but scope is clearly limited to company-financial claims.

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