Arcgis Norman

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds valuable behavioral context: the default free model (Workers AI Llama-3.3-70b), the BYO Anthropic key with direct billing responsibility, and the per-model return structure. No contradictions with annotations.

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

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

Three sentences, front-loaded with purpose and followed by key operational details and use cases. Every sentence earns its place with no fluff or repetition.

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

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

The description covers purpose, default and optional models, cost implications, return format, and use cases. Given the tool's moderate complexity and thorough annotations, it is largely complete, though it omits error handling or interpretation of the combined view.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds some extra meaning by naming the exact default model (Llama-3.3-70b) and clarifying the cost implication for Anthropic, but most parameter details are already in the schema.

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

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

The description clearly states the tool's function: probing LLMs for what they know about an entity and scoring visibility 0-100 per model. It uses a specific verb ('Probe') and resource ('LLMs'), and distinguishes itself from sibling tools like scan_competitor_ai_presence by emphasizing per-model scoring and a combined view.

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

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

The description provides clear usage context: 'Useful for AI-marketing audits, pre-launch brand checks, competitive monitoring.' It does not explicitly name alternatives or exclusions, but the intended scenarios are well defined, earning a 4.

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 behavior beyond annotations by explaining that this tool routes the question across 5,564 tools and returns structured answers with stable pipeworx:// citation URIs. This clarifies the opaque routing behavior that readOnlyHint/idempotentHint do not convey, though it does not discuss failure cases, rate limits, or source freshness.

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

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

The description is longer than ideal but front-loaded with the most important directive, 'PREFER OVER WEB SEARCH'. Some redundancy exists: the long domain list overlaps 'anything requiring authoritative structured data', and the examples reinforce points already stated. Still, the length is largely justified given the tool's broad scope and routing role.

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 sufficiently explains the return form: structured answer with citation URIs. It also covers scope, examples, route behavior, and alternatives. The tool has a single free-text parameter and rich context in the description, so the description is complete enough for an agent to select and invoke it confidently.

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

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

The schema description coverage is 100%, with all parameters being aliases of `question` and the schema already explaining the natural-language expectation. The description gives useful example queries but does not add meaningful parameter-level semantics beyond the schema, so the baseline 3 is appropriate.

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

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

The description clearly identifies what the tool does: routes a natural-language factual question to the appropriate data source/tool among thousands and returns a structured answer with citation URIs. It also distinguishes itself from sibling tools by naming ask_pipeworx_grounded and deep_research as alternatives for specific use cases.

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

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

The description is explicit about when to use this tool: 'PREFER OVER WEB SEARCH', 'START HERE for most questions', and gives many concrete query patterns and examples. It also tells when to step up to ask_pipeworx_grounded or deep_research, offering clear exclusion and alternative 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 state readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable context beyond annotations: it's an experimental edge with candidate routing changes, falls back to nothing, and is a full working router. It also explains that results are compared against the stable router. No contradiction with annotations; credit for adding operational detail.

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

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

The description is concise and front-loaded: opens with the core purpose, then provides usage guidance and key behavioral notes. Every sentence adds value (beta context, current equivalence, fallback clarification), with no fluff. Length is appropriate for the tool's complexity.

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

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

For a tool with no output schema and a single required parameter, the description is complete: it explains the beta nature, current state, usage equivalence, and experimental implications. It also clarifies it's a full router, not a limited fallback. The complexity is moderate, and the description covers all key aspects an agent needs to know.

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 fully documents all parameters. The description does not add parameter-specific meaning beyond noting a universal router with same arguments as ask_pipeworx. Baseline of 3 is appropriate since the schema handles parameter documentation; the description only confirms the alias set indirectly.

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

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

The description clearly states it's a beta version of ask_pipeworx, a universal router with the same tools and arguments. It distinguishes itself by mentioning candidate routing improvements, but it relies on the sibling 'ask_pipeworx' for full differentiation. The verb 'ask' and resource 'pipeworx beta' are specific enough, though not fully standalone.

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 it exactly like ask_pipeworx' and provides clear context on when to use it ('when you want the newest routing'). It also implicitly distinguishes from alternative tools by naming the stable router, and mentions that no candidate is active, so it currently matches ask_pipeworx exactly. This guides the agent on when and how to prefer it.

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 detailed behavioral traits beyond annotations: the tool only uses tool result content, returns a structured refusal with specific reasons (not_in_source, no_tool_match, etc.), and costs an extra LLM call. This is rich context that annotations (readOnly, openWorld, idempotent) do not cover. 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 information-dense and well-structured: it opens with the core purpose, then details the success response shape, refusal reasons, usage context, and cost note. Every sentence adds value with no filler, and the structure makes the behavior 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?

Despite no output schema, the description fully specifies the return format for both success and failure, including evidence fields and refusal_reason enum. It explains the routing behavior, cost implication, and when to prefer the alternative. This is complete for a tool of this complexity.

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

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

Schema coverage is 100% with all six parameters described as aliases for 'question'. The description does not add further parameter-level meaning beyond confirming that a natural language question is the input. Baseline 3 is appropriate since 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 identifies the tool as a 'hallucination-resistant answer mode' with specific verb and resource: it routes through the same selection mechanism as ask_pipeworx, fetches data, and extracts answers only from the tool result. It distinguishes itself from the sibling ask_pipeworx by emphasizing grounded evidence and explicit refusal behavior.

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

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

Explicitly states when to use: 'whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' with examples. Provides a clear exclusion: 'prefer ask_pipeworx for casual lookups' and explains the cost tradeoff. This gives concrete when/when-not guidance.

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

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

Annotations already indicate read-only, open-world, idempotent, non-destructive. The description goes far beyond by disclosing resolver contracts, suppression of analysis on low-confidence matches, status returns for closed/inactive markets, wide-spread tradeability flags, fallback behavior for news sources, and resolution-rule risk (cancellation refund logic). This is rich behavioral context that annotations alone would not provide.

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

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

The description is long but well-structured with labeled sections (CLASSIFIERS, FAN-OUT EXAMPLES, RESPONSE SHAPES, RESOLVER CONTRACT, PARENT_EVENT EXTRACTOR, NEWS FIELDS, SAFETY, RESOLUTION-RULE RISK). It front-loads the core purpose. While not concise, every sentence carries substantive information for a complex tool, so it earns a 4 rather than 5.

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?

There is no output schema, so the description must fully explain return values. It does: response shapes for market/analysis/evidence, resolver contract with confidence and alternatives, parent_event structure, news fallback fields, status codes for block/inactive/illiquid, and cancellation-rule semantics. This is a complete behavioral contract for 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?

Schema descriptions cover all three parameters 100%, including the market input format, depth enum meaning, and include_raw default. The description adds little beyond that—it mentions passing slug/URL/question text and depth defaults, but these are already present in the schema. Thus a 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 first sentence states a specific verb and resource: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It also lists concrete use cases ('should I bet on X') and distinguishes itself from siblings by emphasizing integrated evidence packet and market-vs-model comparison, not just edge calculation.

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

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

Explicitly says 'Use for...' and gives three use-case patterns. It also details when fan-out happens, how low-confidence matches short-circuit, and how closed markets are handled, providing clear context for when to rely on the tool versus alternatives. It doesn't explicitly name alternative tools but the use-case framing and sibling context are sufficient.

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

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

Annotations already mark the tool as read-only, idempotent, and non-destructive; the description adds substantial behavioral context: data sources (SEC EDGAR/XBRL, FAERS, FDA), correct handling of off-calendar fiscal years, sorting by primary metric, and citation URIs. 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?

Though longer than the high-calibration example, every sentence earns its place: trigger phrases, usage preference, type-specific behavior, sorting, and output format. The content is front-loaded with the purpose and immediate usage guidance, with no filler.

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

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

For a tool with two distinct entity modes and no output schema, the description covers data sources, specific metrics returned, sorting behavior, and return format (paired data + citations). This is sufficient for an agent to select and invoke correctly without needing additional structured information.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaningful semantics beyond the schema by explaining what each type pulls (10-K revenue/net income/cash/debt for companies; adverse-event/trial counts for drugs) and how values are interpreted. This enrichment justifies above-baseline scoring.

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 defines the tool as a side-by-side comparison of 2–5 companies or drugs in one parallel call, with specific trigger phrases like 'X vs Y' and 'rank these companies.' It distinguishes itself from single-entity siblings 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?

It explicitly states 'ALWAYS PREFER over sequential single-pack lookups when comparing entities,' giving clear when-to-use guidance. The 2–5 entity limit and trigger examples imply non-comparison tasks should use other tools, effectively providing alternatives.

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

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

Annotations already mark readOnly/idempotent/not-destructive, but the description adds substantial behavioral detail: account requirement and paid depth tier, parallel tool routing, gaps[] for unanswered facets, never-invented evidence, fetchable citation_uri, semantic excerpting, contradictions[] for standard/thorough, and latency ranges. This goes far beyond what annotations provide.

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

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

The description is long but every sentence carries substantive information about usage, limitations, output, depth options, and performance. It is front-loaded with the critical account requirement and immediately contrasts with ask_pipeworx. Some details could be grouped more tightly, but for a tool of this complexity it remains efficient.

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

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

Given there is no output schema, the description compensates by detailing the findings packet contents (verbatim evidence, confidence, source, fetched_at, citation_uri), gaps[], contradictions[], hop fields, and latency. It also covers alternatives, prerequisites, and depth-dependent behavior. This is a complete picture for an AI agent to select and invoke 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?

Schema coverage is 100%, so baseline is 3. The description enriches both parameters: it explains depth values ('quick=3 (single hop)', 'standard=3... gap-recovery hop + contradictions[]', 'thorough=6... full iterative hop') and clarifies the question is in natural language and can be broad. This adds meaningful nuance beyond the enum descriptions, though not perfectly exhaustive.

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 precisely states the tool's function: 'Grounded multi-source research across Pipeworx's 1462 STRUCTURED data sources' in one call, decomposing questions into facets and routing to tools in parallel. It clearly distinguishes itself from open-web search and from siblings like ask_pipeworx. The verb 'research' plus the resource scope and output packet make purpose unmistakable.

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

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

Explicit when-to-use guidance is provided: 'Best for broad/multi-part questions over structured data', with concrete examples. It also gives exclusions: 'For a single lookup use ask_pipeworx' and 'For BREAKING or colloquial CURRENT-NEWS... prefer ask_pipeworx'. It even covers the auth prerequisite, telling unsigned-in users to use ask_pipeworx instead.

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

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

Annotations already indicate readOnly, idempotent, non-destructive behavior. The description adds valuable context: results include full schemas with examples, are ready to call directly, and no second lookup is needed. It does not contradict annotations and provides useful operational detail, though it omits edge cases like no results.

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

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

The description is three sentences with a clear front-loaded purpose. The list of domains is long but directly informs the agent of searchable topics. Every sentence earns its place, 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?

There is no output schema, but the description explains return values (top-N tools with schemas and examples). It covers when to use, what inputs are expected, and result format. Minor gaps like limit default are covered by the schema. Overall complete for a discovery tool.

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

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

Schema coverage is 100% with detailed descriptions for every parameter (query, limit, and aliases). The description references 'top-N' which maps to the limit parameter, but does not add significant meaning beyond the schema. Baseline 3 is appropriate because the schema fully documents parameters.

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

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

The description clearly states the tool's function: 'Find tools by describing the data or task.' It lists many domains and explicitly says it returns top-N relevant tools with names, descriptions, and schemas. This distinguishes it from sibling tools by positioning it as a meta-discovery 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?

The description gives explicit usage guidance: 'Use when you need to browse, search, look up, or discover what tools exist for...' and instructs to 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This clarifies the discovery context and differentiates from using a specific tool directly.

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

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

Beyond the read-only and idempotent annotations, the description reveals significant behavioral details: it fans out across multiple sources, returns specific fields (filings, fundamentals, patents, news, LEI), includes output limits ('up to 5'), and discloses technical caveats like the USPTO API sunset and GDELT→GNews fallback.

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 extremely efficient—each sentence earns its place. It starts with user-intent examples, then states the core function, enumerates sources and return fields, and ends with parameter constraints. No fluff or redundancy; the layout logically flows from examples to technical specifics.

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 of this complexity with no output schema, the description is remarkably complete. It covers input restrictions, the full fan-out behavior, output structure, fallbacks, soft-fail behavior, and even names the upstream API sunset. Nothing essential is missing.

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

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

The input schema already fully documents both parameters with 100% coverage, including the enum for 'type' and examples for 'value'. The description repeats the same information (ticker or zero-padded CIK, names not supported) but adds no new semantic details beyond the schema, so baseline 3 is appropriate.

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

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

The description clearly states the tool's function: producing a full cross-source profile of a US public company with illustrative examples like 'Tell me about X' and 'company profile for Microsoft'. It explicitly distinguishes itself from sibling tools by stating 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups' when a holistic view is requested.

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

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

The description gives explicit when-to-use guidance ('when the user asks for a holistic view') and identifies an alternative ('use resolve_entity first if you only have a name'). It also tells the agent to prefer this tool over chaining single-source lookups for holistic 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 already declare destructiveHint=true and readOnlyHint=false. The description adds context about what to delete (stale or sensitive data) but does not cover edge cases like missing keys, though idempotentHint partially mitigates this.

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

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

Two sentences, no filler, front-loaded with the primary action and immediately followed by practical usage guidance. Every sentence contributes value.

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

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

For a simple single-parameter, destructive operation with strong annotations, the description adequately covers purpose, usage scenarios, and relationship to sibling tools. The absence of an output schema is acceptable for a delete 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?

The schema covers the 'key' parameter completely (100% coverage), and the description mentions 'by key' but adds no further details on format or validation. It meets the baseline expected when schema is comprehensive.

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

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

The description uses the explicit verb 'Delete' with resource 'previously stored memory' and method 'by key', making the tool's function unmistakable. It clearly distinguishes it from sibling tools like 'remember' and 'recall'.

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

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

It provides explicit use cases ('context is stale, task is done, clear sensitive data') and names companion tools 'remember and recall'. However, it does not explicitly state when not to use the tool, which is a minor omission.

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 context about the process: fetches the page, extracts title/description/key links, emits standard markdown, and outputs a text blob. This goes beyond the annotation hints without contradicting them.

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

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

The description front-loads the core function in the first sentence, explains the process in the second, and lists use cases in a compact final segment. 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?

With no output schema, the description adequately describes the output as a 'single text blob' in 'standard llms.txt markdown format.' The tool's behavior and use cases are covered; minor omissions like error handling are acceptable for this simplicity.

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?

Both parameters are fully described in the schema with 100% coverage. The description mentions 'key links' which loosely relates to max_links but adds little beyond the schema. Baseline of 3 is appropriate.

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

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

The description clearly states the tool's function with a specific verb and resource: 'Generate a production-ready llms.txt file for any URL.' It distinguishes itself from sibling tools by detailing the extraction and emission process, including the standard markdown format.

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

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

The 'Useful for' section provides explicit scenarios—getting a client's site indexed, drafting for own project, auditing competitor visibility. No explicit alternatives are named, but the context is strong enough to signal appropriate use.

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

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

Annotations already disclose read-only, idempotent, and non-destructive behavior, covering the safety profile. The description adds the specific return fields but does not mention potential performance costs of counting records or any network/auth prerequisites, so the added behavioral context is limited.

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?

A single, front-loaded sentence that clearly states the action and resource, then compactly lists all the information returned. Every element earns its place 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 the tool's simplicity (one parameter), rich annotations, and no output schema, the description sufficiently conveys what the agent should expect: schema fields, geometry type, record count, and capabilities. It does not explain error handling, but that is not critical for this straightforward metadata lookup.

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

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

The schema description for the sole url parameter is 100% comprehensive, including an example, so the baseline is 3. The tool description merely echoes 'by url' without adding any new semantic detail beyond the schema.

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

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

The description uses the specific verb 'Get' and clearly identifies the resource as an ArcGIS Feature/Map Service layer's schema. It enumerates the exact outputs (fields, geometry type, total record count, capabilities), making it distinct from sibling tools like query_layer that likely handle feature 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 clearly implies this tool is for schema/metadata retrieval when you have a layer URL. It does not explicitly name alternatives or exclusions, but the context is strong enough (schema vs. data query) to guide selection within the sibling toolset.

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

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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds value by listing the exact return fields (id, type, params, created_at, last_fired_at, fire_count) and clarifying that active subscriptions are returned by default, with inactive ones optionally included. This goes beyond annotation declarations.

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

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

The description is three sentences, each earning its place: the first states the core action, the second lists return fields, and the third gives practical use cases. It is concise and front-loaded with purpose.

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

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

With no output schema, the description compensates by explicitly listing the returned fields. It also gives usage context. Missing details like pagination or ordering are minor for a simple read-only list tool, so the description is nearly complete but 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 schema fully documents the sole parameter include_inactive with a clear description, so the tool description adds no additional semantic value. Per the calibration baseline, a score of 3 is appropriate when schema coverage is high and the description does not further elaborate.

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

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

The description clearly states the tool lists the caller's active subscriptions, using a specific verb and resource. It distinguishes itself from sibling tools like subscribe and unsubscribe by explicitly focusing on the read-only listing action.

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

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

The description provides explicit guidance on when to use this tool: to review what's being monitored before adding more subscriptions or to find an ID to cancel. This frames its purpose within the workflow, though it does not mention alternatives beyond 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?

The description discloses behavioral details beyond annotations: the claim_token return flow for unauthenticated filings, how to later query resolution status, rate-limiting to 5 per identifier per day, and that it is free and does not count against tool-call quota. These are meaningful behaviors that annotations do not convey, and nothing contradicts 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 detailed yet efficiently written. Every sentence serves a purpose: defining use cases, setting boundaries, explaining the claim_token mechanism, setting expectations on response time and rate limits, and addressing quota concerns. No redundant phrases; the structure reads logically from action to scope to post-submission behavior.

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

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

Given the tool has four parameters, nested context objects, no output schema, and no annotations indicating safety, the description provides a very complete picture. It covers what happens without an account (claim_token), how to follow up, rate limits, and the intended audience (Pipeworx team). The absence of an explicit return schema is compensated by the claim_token explanation, making the tool's behavior predictable.

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

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

Although schema coverage is 100%, the description enriches parameter semantics significantly. It explains the claim_token usage pattern ('pass it back later as pipeworx_feedback(...)'), and clarifies message content expectations ('Describe the issue in terms of Pipeworx tools/packs — don't paste the end-user's prompt'). This goes beyond what the schema alone provides.

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

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

The description opens with a clear, specific purpose: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It enumerates concrete trigger types (bug, feature, data_gap, praise) and clarifies scope by restricting to Pipeworx-served tools, effectively distinguishing this from sibling research/discovery 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?

It provides explicit when-to-use guidance by listing bug, feature/data_gap, praise, and explicit when-not-to-use for tools from other MCP servers with a clear rationale ('we cannot fix it and reporting it here only delays you'). Also offers a fallback check ('Not sure? Pipeworx tool names are the ones this connection lists'), making the decision boundary highly actionable.

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

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

The description adds significant behavioral context beyond the annotations: it discloses the self-aggregating nature, data source (CF analytics-engine), no PII, and cache duration (5min-1h). This gives the agent a clear picture of data freshness and privacy implications.

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: the opening sentence states the core value, followed by a concise 'Useful for' list. Every sentence adds substantive information, and it remains compact without padding.

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 one optional parameter, strong annotations, and no output schema, the description fully covers what is returned (top tools, top packs, volume) and why an agent would need it. The three use cases provide sufficient context for tool selection.

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

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

Schema description coverage is 100%, as the single 'window' parameter has a full description with enum values, default, and semantics. The tool description's mention of windows is redundant with the schema, so no additional value is added beyond the baseline.

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

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

The description clearly states the tool's function with a specific verb+resource: 'Returns the top tools, top packs, and total call volume' over a recent window. It distinguishes itself from siblings by focusing on aggregated AI agent call trends rather than individual tool functionality.

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 explicit use cases ('Useful for...'), giving clear context for when to invoke this tool. However, it does not explicitly name alternatives or state when not to use it, which would merit a 5.

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

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

Beyond the annotations (readOnly, openWorld, idempotent), the description discloses internal behaviors: SEMANTIC ANCHOR uses Jaccard similarity at ≥0.30, PARTITION FILTER drops placeholder slugs and returns null for >20% placeholder fraction, and FILL CHECK prices against live CLOB depth, warning that realizable_edge_pp <= 0 means do not trade. This adds substantial operational context without contradicting annotations.

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

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

The description is long but dense with necessary operational detail, front-loading purpose and mode selection. It repeats partition_check details and could be condensed with bullet lists, but the verbosity is justified by the tool's complexity, making it appropriately sized.

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

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

The tool is complex with multiple modes, filters, and a fill-check sub-process, and there is no output schema. The description covers default behavior, both parameter modes, response shapes (opportunities[], partition_check fields), filter semantics, and trade advisories, leaving very few gaps for an agent to misuse 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?

Though the schema provides 100% coverage for both parameters, the description adds significant meaning: it introduces the no-args trending_scan mode not visible in schema, gives concrete example slugs and seed questions, explains event vs topic behavior deeply, and clarifies which mode is recommended for a specific market. This far exceeds the basic 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 opens with 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks', using a specific verb and resource. This clearly distinguishes the tool from siblings like polymarket_fill_risk (pricing) and polymarket_edges by focusing on monotonicity/partition-sum arbitrage.

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

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

It explicitly delineates three invocation modes: no args for trending_scan, `event` for single-event partition_check, and `topic` for cross-event scanning. It provides recommended usage per situation and names polymarket_fill_risk as an alternative for custom sizing, giving clear when-to-use guidance.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, providing a safe-read baseline. The description goes far beyond this by disclosing caching behavior ('Cached 1h at the KV level'), response structure, a 24h-move warning, the placeholder-slug filter, and diagnostics for empty segments. It also details what fields every opportunity carries, making the tool's behavior highly transparent without contradicting annotations.

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

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

The description is long but well-structured: it starts with the purpose, then breaks down model families, response fields, knobs, and diagnostics. Each section adds substantive information, and there is little waste. However, the density and length make it less concise than ideal, even though the structure helps navigate it.

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 carries the full burden of explaining return values, and it does so comprehensively. It details the top-level by_segment structure, per-opportunity fields (edge_pp_net, kelly_fraction, etc.), the fed_candidates/fed_note section, and _diagnostics with funnel counters. It also explains why segments can be empty, covering all necessary context for complete understanding of the tool's output.

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

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

Schema coverage is 100%, with each parameter already having a detailed description (e.g., min_kelly, min_edge_pp, slippage_pp, and the tradeable-edge filters). The description references the knobs but does not add significant meaning beyond the schema; it only provides a top-level grouping ('TRADEABLE-EDGE KNOBS') and notes that cache keys include all knobs. Since the schema handles parameter semantics well, a baseline score of 3 is appropriate.

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

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

The description opens with a specific verb+resource+scope: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' This clearly states what the tool does, and the phrase 'Built for what should I bet on today' establishes its purpose. It also distinguishes itself from siblings by focusing on top markets and avoiding the need to page through hundreds, making it unique among the listed 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 clear context for when to use the tool ('Built for what should I bet on today') and explains how to use certain knobs (e.g., min_liquidity / max_spread_pp to drop unrealizable edges, min_partition_leg_kelly to filter thin partitions). It also gives guidance on interpreting results, such as the fed_note explaining why Fed bets are excluded. However, it does not explicitly compare itself to sibling tools like polymarket_arbitrage or polymarket_edge_tracker, so it lacks explicit alternative-exclusion 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 only declare safe read-only behavior (readOnlyHint, idempotentHint, destructiveHint). The description goes far beyond this by explaining the 60-day snapshot TTL, that snapshots are written on cache-miss causing gaps, that decay is computed on absolute value with sign preserving trade direction, and that numbers come from daily closes of edge_pp_net rather than intraday. This is rich behavioral context that adds real value 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 longer than average but well-structured with 'RESPONSE:' and 'LIMITS:' sections. Every sentence adds value, but some repetition exists (e.g., edge_pp_net explained multiple times). It is dense but not bloated, earning a 4 rather than a 5 for slight 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?

There is no output schema, so the description carries full burden for explaining return values. It thoroughly describes tracked[], expired[], and snapshot_dates[] including fields like first_seen, trend, decay_pp_per_day, and lifespan_days. It also covers storage limitations and data freshness, making the tool fully understandable without an output schema.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaningful detail: it states defaults ('default 14', 'default 1wk'), max for days ('max 30'), and expands window enum values ('24hr | 1wk | 1mo'). It also explains that days controls lookback and window selects the snapshot family, connecting parameters to their effect on the response.

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

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

The description clearly states the tool's purpose: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots.' It uses a specific verb ('Answers') and resource ('edge persistence and decay'), and distinguishes itself from sibling tools like polymarket_edges by focusing on time-series tracking and decay rather than computing current edges.

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

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

The description gives clear context for when to use the tool, such as 'how long has this edge existed and is it shrinking?' and notes that 'a fresh wide edge and a 3-week-old wide edge are different trades.' It also explains limitations (TTL, gaps) that inform usage, but it does not explicitly name alternative tools to use instead, so it stops short of explicit when-not use.

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

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

Annotations declare readOnly, openWorld, idempotent, non-destructive; the description adds substantial behavioral context beyond those: walks the order-book ladder, interprets size_usd differently per mode, computes verdicts, and explicitly names the dominant loss mode (unhedged directional risk from partial basket fills). 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 long but well-structured with SINGLE-MARKET and BASKET labels, front-loaded definition, and requirements. Every sentence adds operational detail; however, the density and use of ALL-CAPS makes it slightly harder to parse quickly, keeping it from a 5.

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

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

No output schema exists, so the description carries the burden of explaining return values. It enumerates returned fields for both modes (top_of_book, vwap_fill_price, verdict; theoretical_sum, capture_ratio, forced_directional_risk, etc.) and covers interpretation of size_usd, mode requirements, and risk caveats. This is comprehensive for a two-mode 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% (all 4 parameters documented), so baseline is 3. The description adds meaningful semantics: size_usd is 'max spend on buys, target proceeds on sells' for single-market and 'settlement notional S (shares per leg)' for basket, plus side auto behavior in basket mode. This goes beyond the schema's basic descriptions.

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

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

The description states a specific purpose: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It clearly distinguishes this tool from siblings by tying it to polymarket_arbitrage and polymarket_edges signals and explaining the fill-risk gap it addresses.

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

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

Explicit guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It explains both single-market and basket modes and when each applies, and warns about partial basket fills converting arb into unhedged directional positions.

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

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

The description goes far beyond the annotations by detailing compatibility_warning triggers, temporal alignment meaning, skipped_cross_type/subtype counters, and why matched_pairs:0 can indicate different bet shapes or unrelated events. It also discloses that pre-mapped topics are often not tradeable, which is highly useful operational context. No contradiction with the readOnly/idempotent hints.

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

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

Although long, the description is dense and front-loaded: purpose, modes, response, safety fields, and caveats are clearly labeled and all sentences contribute essential information. The structure uses bold labels and logical sections, making it easy for an agent 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?

Since there is no output schema, the description carries the burden of explaining return values and edge cases; it does so thoroughly with leg-by-leg prices, spread fields, compatibility warnings, temporal alignment, and skipped counters. It also covers limitations and practical use, making the tool fully understandable without 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?

The input schema already provides 100% coverage with descriptions and examples for all three parameters, so the baseline is 3. The description adds value by listing the exact topic enum, explaining how explicit parameters override the mapped side, and clarifying the two modes of operation.

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

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

The description states a specific verb+resource: computing the cross-venue spread between Kalshi and Polymarket for the same resolving question. It distinguishes from sibling tools by emphasizing the two-venue comparison and the compatibility-warning logic, making the tool's unique scope clear.

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

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

It explicitly explains two input modes (topic shortcuts vs explicit ticker/slug) and when each is appropriate, plus warns that pre-mapped topics often return compatibility_warning. However, it does not name sibling alternatives such as polymarket_arbitrage or polymarket_edges as explicit 'use this instead' 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 readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds value by disclosing that the tool returns attribute rows and geometry, that the where clause is SQL-like, and that limit/offset support pagination. The sampling tip is also a useful behavioral nuance. 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 exactly two sentences. The first sentence front-loads the action and parameter list; the second gives a memorable sampling tip. No wasted words, no repetition of schema fields.

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 moderate complexity (6 params, 1 required, no output schema), the description covers the essential aspects: purpose, parameter behavior, return type, and a usage flow via search_datasets. It omits explicit max limit or error behavior, but those are partly covered by the schema (limit max 2000) and the overall simplicity. The description is sufficient for effective agent use.

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

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

Schema coverage is 100%, so the schema already documents all six parameters. The description reiterates the parameter list in a compact form and adds a small usage tip, but it doesn't materially extend the meaning 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 opens with a specific verb+resource: 'Query an ArcGIS Feature Service / Map Service layer by its url (from search_datasets).' It lists the key query parameters (where, out_fields, order_by, limit, offset) and states the return type ('Returns attribute rows (and geometry)'). This clearly distinguishes it from siblings like layer_info (metadata) and search_within (spatial search).

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

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

The description gives clear context by mentioning the URL should come from search_datasets, implying a workflow: first find the dataset, then query it. It also provides a practical sampling tip ('Use where="1=1" + out_fields="*" to sample'). However, it does not explicitly state when not to use this tool or name alternatives, so it falls short of a full 5.

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

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

Beyond the annotations, the description adds useful context about scoping to 'anonymous IP, BYO key hash, or account ID' and the ability to list all keys by omitting the argument. This does not contradict the readOnlyHint and idempotentHint annotations.

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

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

The description is three purposeful sentences, leading with the primary action and then adding scoping and related-tool context. No redundancy or filler.

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

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

For a simple read-only tool with one optional parameter and no output schema, the description adequately covers operation, scoping, and sibling relationships. It could optionally include return format or not-found behavior, but the core usage is clear.

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

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

The schema already has 100% coverage for the optional 'key' parameter, but the description enriches it with concrete examples like 'user's target ticker, an address, prior research notes' and clarifies the dual behavior when the key is omitted.

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 retrieves a previously saved value or lists all saved keys, using the specific verb 'Retrieve'. It also distinguishes itself from siblings by referencing 'remember' to save and 'forget' to delete.

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

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

It clearly states when to use the tool: 'Use to look up context the agent stored earlier... without re-deriving it from scratch.' It also gives pairing guidance with 'remember' and 'forget', and explains the scoping by identifier.

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?

Annotation contradiction: readOnlyHint=true conflicts with the description's claim that setting mark_read:true flags returned events as read, causing a side-effect (mutating read state). This directly contradicts the read-only hint. The description is transparent about the side-effect, but the annotation implies no mutation, making the overall behavioral disclosure inconsistent.

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

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

The description is four sentences, each adding value: main action, return payload details, filtering and mark_read behavior, and polling plus an alternative URL. It is front-loaded with the primary purpose and avoids redundancy.

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

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

Given the tool has no output schema, the description compensates by indicating the return fields (source, citation_uri, raw payload) and the effect of mark_read. It also mentions the persisted feed and an alternative REST endpoint. It doesn't detail limit/unread_only behavior, but those are fully covered by the schema, so the description is reasonably complete.

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

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

Schema description coverage is 100%, so all parameters (type, limit, since, mark_read, unread_only) have clear definitions. The description reinforces type, since, and mark_read but adds no new semantics beyond the schema. Baseline 3 is appropriate given the schema does the heavy lifting.

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

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

The description clearly states the tool's purpose: 'Pull fired events from your subscription feed' and specifies the return content (source, citation_uri, raw event payload). It is distinct from sibling tools like list_subscriptions (which lists subscriptions) and recent_changes (which tracks changes).

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 practical usage context: supports filtering by type and since, explains mark_read behavior, and notes that polling works fine. It also offers an alternative HTTP endpoint for scripts/dashboards. However, it does not explicitly state when not to use this tool versus the sibling search/recent tools, so it stops short of a 5.

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

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

Annotations already declare readOnly, non-destructive, and idempotent behavior, so the description is not required to restate these. It adds valuable context: parallel fan-out to multiple data sources, GDELT→GNews fallback on rate limits/5xx, a soft-fail for USPTO due to PatentsView API sunset, and the return structure (changes[] grouped by source + total_changes + citation URIs). This goes beyond annotations without contradicting them.

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

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

The description is a single dense paragraph but well-organized: front-loaded with query examples, then source specifics, parameter details, return value summary, and an alternative tool. Every sentence adds necessary operational information, so it earns its place. Slightly longer than minimal but justified by the tool's multi-source complexity.

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

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

With no output schema, the description fully carries the burden of explaining return values, and it does: 'structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs.' It also covers edge cases (fallbacks, API sunset, soft-fail), parameter formats, and provides an alternative tool. This is complete for a tool of this complexity.

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

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

Schema coverage is 100%, so the baseline is 3. The description enriches parameter understanding by specifying that `since` accepts ISO dates or relative shorthand ('7d', '30d', '3m', '1y') with a recommendation ('Use "30d" or "1m" for typical monitoring'). It also clarifies that `value` can be a ticker or zero-padded CIK, and that `type` currently supports only 'company'.

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

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

The description opens with natural-language query examples ('What's new with X', 'latest on Y') that make the tool's purpose immediately understandable, then states it is a 'change feed for a company in the last N days/weeks/months in ONE parallel call.' It clearly distinguishes itself from the sibling entity_profile tool by specifying that entity_profile provides the static profile regardless of window.

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

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

The description provides explicit usage context: it covers time-windowed change queries across SEC, news, and patents. It also gives a direct alternative: 'Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.' Additionally, it explains fallback behavior between GDELT and GNews, which helps the agent decide when this tool is appropriate.

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

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

Adds context beyond annotations: key-value pair storage, scoping by identifier, persistent memory for authenticated users, 24-hour retention for anonymous sessions. This is valuable behavioral info not in 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 well-organized, front-loaded with purpose, and includes usage guidance, storage behavior, and related tools 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?

For a simple two-parameter tool, the description covers purpose, usage, storage details, retention, and related tools. No output schema, but the description is 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 covers both parameters with descriptions (100% coverage). Description adds context about key-value pair storage and identifier scoping but does not significantly change meaning beyond schema.

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

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

The description uses the specific verb 'Save' and identifies the resource as 'data the agent will need to reuse later,' with clear scope across conversations/sessions. It also distinguishes from siblings by mentioning recall and forget.

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

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

It explicitly states when to use: 'Use when you discover something worth carrying forward' with concrete examples. It also pairs with recall and forget, implying 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 adds substantial behavioral context beyond the annotations (which already declare readOnly, idempotent, openWorld). It details cascading internal lookups, graceful degradation if GLEIF or OpenFIGI is unavailable, and explicit handling of unresolved identifiers under an 'unresolved' field. It also explains how ISINs resolve to legal entities via GLEIF. This level of detail is highly valuable for an agent.

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

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

The description is quite long and dense, covering many details in a single paragraph with embedded sub-bullets. It is front-loaded with example queries, which is good, but the amount of detail could overwhelm some agents. While every sentence adds value, the structure could be more concise (e.g., separate sections for each type). Still, it is informative and well-organized.

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

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

Given the tool's complexity (multiple entity types, cascading lookups, graceful degradation, unresolved identifiers) and the absence of an output schema, the description is remarkably complete. It explains what each type returns, how identifiers are labelled, and what happens when lookups fail. No output schema is needed because the description effectively documents the return structure.

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

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

The input schema already has 100% description coverage for both parameters, including enum values for 'type' and examples for 'value'. The description adds further semantic richness: for 'company', it explains the cross-source identity spine (CIK, ticker, LEI, FIGI) and that ISINs are accepted. For 'drug', it mentions RxNorm citations. This goes beyond the schema's minimal descriptions.

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

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

The description uses specific verbs like 'resolve' and 'look up' and clearly states the tool's purpose: converting user-spoken names into canonical/official identifiers. It provides numerous example queries ('What's the ticker for…', 'find the CIK for…') and distinguishes between entity types (company, drug). While it doesn't explicitly differentiate from siblings like 'entity_profile' or 'compare_entities', the purpose is unambiguous and self-contained.

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

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

The description explicitly advises 'Use FIRST whenever you have a name but need an ID', providing a strong when-to-use directive. It also notes that the tool replaces 2-3 manual lookups, implying efficiency. However, it does not mention when NOT to use it (e.g., if you already have an ID) or suggest alternatives like 'entity_profile' for more detailed entity information. Clear context, but no exclusions.

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

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

Annotations already declare read-only, idempotent, and non-destructive. The description adds meaningful context: it probes each entity via ai_visibility_check, ranks by score, and returns per-entity metrics. This goes beyond structured annotations, though it doesn't discuss rate limits or latency from multiple probes, which would be useful but not critical given the safety hints.

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

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

The description is three sentences, front-loaded with the primary action, then the mechanism, a use case, and output format. Every sentence adds value with no repetition or fluff. It is appropriately sized for the tool's moderate complexity.

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

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

With no output schema, the description compensates by specifying the return format (ranked list with score, confidence, signal density). It also gives a concrete example question. It does not mention parameter constraints (2-8 entities) that are in the schema, but that's acceptable. Overall, it provides enough context for an agent to decide and invoke correctly.

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

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

Schema coverage is 100%, with detailed descriptions for each parameter (e.g., entities first entry as subject, models supported, _apiKey condition). The description reinforces the 'your brand + N competitors' concept but adds no new parameter semantics beyond the schema. Baseline 3 is appropriate because the schema carries the full load.

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

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

The description opens with a specific action: 'Compare AI visibility across multiple entities side-by-side.' It clearly distinguishes from sibling ai_visibility_check by indicating it probes multiple entities and ranks them. The mention of returning a ranked list with score/confidence/signal density further clarifies the tool's specific output.

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 states a clear use case: 'Useful for competitive AI-marketing audits' with an example question. It implicitly differentiates from ai_visibility_check by describing batch comparison, but it does not explicitly name alternatives or provide when-not-to-use guidance. Still, the context is strong enough to guide selection.

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

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

The description adds significant context beyond annotations: it details the composite behavior, return payload structure, partial failure degradation, and timing expectations ('bundlephobia's first measurement on a new version can take 5-30s'). Annotations already declare read-only/idempotent, so no contradiction.

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

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

The description is longer but every sentence earns its place: purpose, usage trigger, output details, ecosystem scope, and edge-case behavior are all covered. It is front-loaded with the primary purpose and well-structured for a complex composite tool.

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 enumerates the returned fields (is_latest, license, bundle sizes, etc.), per-advisory detail, links, and alternative versions. It also covers ecosystem limitations and failure modes, making it complete for an agent to invoke correctly.

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

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

Schema description coverage is 100%, with both parameters already documented (e.g., 'Scoped packages are accepted', 'Defaults to the latest published version'). The description adds no further parameter-specific semantics, but the baseline stays at 3 when schema covers everything.

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 'Composite should I add this npm package to my project check' that fans out across deps.dev and bundlephobia. It specifies the exact resources and distinguishes itself from sibling tools by its unique composite nature and focus on npm packages.

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

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

Explicitly says 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. Also provides an exclusion: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly', directing users to alternative behavior for other ecosystems.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds value by disclosing the exact return fields (name, summary, record_count, owner/org, Feature Service url) and how the url should be used downstream, which goes beyond the annotations.

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

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

The description is two sentences, front-loaded with the main purpose, and contains zero redundant or filler content. It efficiently packs scope, return fields, and downstream tool references.

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/discovery tool with no output schema, the description enumerates the return fields and explains how to continue the workflow with query_layer/layer_info. Combined with the fully documented schema and strong annotations, an agent has everything needed to select and invoke the tool correctly.

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

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

Schema coverage is 100%: all three parameters (limit, query, org_id) have descriptive text. The description adds minimal parameter-specific meaning beyond the schema (only mentions keyword search generically), so the baseline 3 applies.

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

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

The description uses the specific verb 'Search' with a clear resource: 'City of Norman GIS open geospatial datasets'. It lists example dataset types and explicitly states what is returned, distinguishing it from sibling tools like query_layer and layer_info by positioning it as the discovery step.

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 clearly implies a workflow: search for datasets, then pass the returned url to query_layer or layer_info. This gives contextual guidance on when to use this tool versus data-querying siblings, but it does not explicitly state when not to use it (e.g., if a dataset URL is already known).

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 substantial context beyond annotations: BGE-base-en embeddings, 500-char overlapping windows, 200K char cap with truncation flag, and return structure (passages with character offsets and similarity scores). This fully discloses behavior.

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

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

The description is four sentences, each packed with purpose, use case, pairing, and technical detail. No fluff; every clause earns its place. It is front-loaded with the core function and uses bolding for key phrases, aiding skimmability.

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

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

Despite lacking an output schema, the description fully explains return values (top-N passages with offsets and similarity scores), input constraints (200K char cap, truncation), and operational details (embedding model, window size). It is complete for a semantic search tool with no extra state.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by clarifying 'text' as content already pulled (e.g., SEC 10-K body) and providing concrete query examples that illustrate intent. It also reinforces the 200K char limit present in the schema. Minor addition for 'limit' but overall sufficient.

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: 'Semantic search INSIDE a fetched record' with a specific verb and resource. It distinguishes itself from siblings by naming ask_pipeworx_grounded as a partner and contrasting with fetching via the gateway, making the scope obvious.

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 when-to-use guidance: 'Use when the record is too big to cram into the prompt'. It explains the benefit (saves context, returns only passages with offsets) and pairs with ask_pipeworx_grounded, providing clear usage context and 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?

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description adds critical behavioral details: OAuth requirement, always-on feed behavior, optional email/SMS with phone verification and 10/day cap, webhook HMAC signing secret returned only once, and auto-disable after 10 consecutive failures. These go far beyond what annotations or schema provide.

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

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

The description is dense but well-structured: it front-loads the core purpose, then systematically covers types, delivery channels, and prerequisites. Every sentence adds essential information; while long, it avoids fluff. Slightly less structured formatting (paragraph vs. bullets) costs a point but remains effective.

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

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

Given the tool's complexity (3 params, nested objects, no output schema), the description covers all critical aspects: return value, authentication requirements, per-type params, delivery options with failure behaviors, and alternative access via recent_alerts. It leaves no significant gaps for an agent to invoke correctly.

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

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

Schema coverage is 100%, so baseline is 3. The description enhances parameters by providing concrete examples for each type (sec_8k items, polymarket_edge topic, fred_series series_id) and elaborating on delivery channel semantics (webhook signing, validation, auto-disable). This adds meaningful value over the schema's terse descriptions.

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

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

The description clearly states the tool's function: 'Create a proactive monitoring subscription to a live-data event stream' and indicates it returns the new subscription ID. This specific verb-object pair ('create subscription') distinguishes it from siblings like list_subscriptions, unsubscribe, and recent_alerts.

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

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

The description provides strong usage context: it requires a Pipeworx OAuth account (excluding anonymous/BYO), enumerates supported subscription types with example parameters, and mentions alternative retrieval via recent_alerts for the always-on feed. It does not explicitly name sibling tools for 'when not to use' but clearly implies 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 convey readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, lowering the bar. The description adds that results are drawn from the live catalog of thousands of tools, returns example questions with tool+argument shapes, and supports optional topic filtering – enriching behavioral context beyond the structured fields.

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?

Although long, the description earns every sentence: it opens with vivid example queries, then explains the output, parameter behavior, and when to use it. Nothing is wasted, and the structure is effectively front-loaded for an onboarding tool.

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 compensates by explaining the return value (category-bucketed example questions with tool+argument shapes), call patterns (no args vs topic), and integration with the live tool catalog. Combined with rich annotations, this is complete for an agent to use the tool properly.

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 already carefully describes the optional topic parameter with allowed values and the effect of omitting it. The description's mention of passing topic for focus and omitting for full spread simply restates the schema, adding no new semantic information, so baseline 3 is appropriate.

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

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

The description clearly identifies the tool as the onboarding entry point that returns category-bucketed example questions with the exact tool and argument shape for each. This specific verb+resource framing distinguishes it from siblings like discover_tools or deep_research, 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?

It explicitly instructs to use this FIRST when unsure what Pipeworx can do, and to learn how to call meta-tools such as ask_pipeworx, entity_profile, and compare_entities. This provides direct when-to-use guidance and names alternatives, fulfilling the highest bar for this dimension.

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 non-destructive and idempotent behavior, but the description adds essential context: ownership enforcement, deactivation instead of deletion, and preservation of historical events via recent_alerts. This explains why destructiveHint is false and adds value 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 the action, and every sentence earns its place. Zero 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 one-parameter tool with no output schema, the description covers the core action, ownership constraints, data behavior, and relationship to recent_alerts. This is sufficient for an agent to invoke it correctly.

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

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

The schema covers the single parameter fully ('Subscription id (uuid) returned by subscribe'), so the baseline is 3. The description mentions 'by id' but does not add new meaning beyond the schema's parameter description.

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

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

The description clearly states the action ('Cancel a subscription by id') and the resource (subscription), distinguishing it from siblings like subscribe and list_subscriptions. It also clarifies the behavior is deactivation rather than deletion, adding specificity.

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

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

The description implies when to use the tool (to cancel a subscription) and mentions the ownership constraint. However, it does not explicitly contrast it with alternatives like list_subscriptions for finding subscriptions or recent_alerts for historical events, leaving the exclusion implicit.

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 (readOnlyHint=true, etc.) already indicate a safe read-only operation, but the description adds substantial behavioral context: it details the two execution paths, the specific verdict types, and the critical caveat that 'could_not_verify' means the check did not happen and must not be shown as evidence. It also clarifies the meaning of 'unsupported'. This goes far beyond annotations and gives callers correct expectations.

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 every sentence adds value. It is well-organized: starts with query examples, then when-to-use, routing logic, output format, important caveats, and an efficiency note. There is no fluff or repetition; the complexity of the tool justifies the length.

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

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

Given no output schema, the description fully explains return values: verdict types, actual value with citation, and reasoning. It also covers error semantics (could_not_verify, unsupported) and the two processing paths. The description is complete enough for an agent to use the tool correctly without additional documentation.

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

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

Although schema coverage is 100%, the description enriches parameter understanding beyond the schema. It explains that tolerance_pct overrides the tolerance implied by the claim wording, suggests setting 1–2 for hallucination detection, and states the default behavior (implied by wording, capped at 5). The claim parameter is also exemplified. This added guidance is directly actionable for an agent.

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

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

The description clearly states the tool's purpose: natural-language claim verification against authoritative sources. It provides concrete example phrasings ('Is it true that…', 'fact check', 'verify the claim that') and distinguishes it from sibling tools by focusing on verification rather than general Q&A or research. The scope is explicit (company-financial vs. any other factual claim).

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 'when to use': whenever the agent needs to check whether something a user said is factually correct. It also explains the routing behavior (company-financial claims via SEC EDGAR fast path, others via grounded pipeline) and notes it replaces 4–6 sequential calls. However, it does not explicitly mention when not to use it or compare it to sibling tools like ask_pipeworx, so it lacks full when-not/alternatives guidance.

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