Amtrak

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

Adds context beyond annotations: default free model, _apiKey passed through to Anthropic, per-model score structure. Annotations already indicate safe read idempotent operation, and description confirms this without contradiction.

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

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

Concise, front-loaded with purpose, then details. Every sentence adds value with no redundancy.

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

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

Given 4 params and no output schema, description fully explains tool behavior, return structure (per-model scores + combined view), and parameter usage. Complete for its 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 baseline is 3. Description adds value by explaining default model, when to provide _apiKey, and purpose of context, enhancing practical understanding.

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

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

The description clearly states it probes LLMs for knowledge about an entity and returns visibility scores (0-100). It distinguishes from siblings like ask_pipeworx or entity_profile by focusing on AI visibility across models.

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

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

Describes use cases (AI-marketing audits, pre-launch checks, competitive monitoring) and explains default model vs. when to provide _apiKey. However, lacks explicit when-not-to-use or comparison to alternatives like deep_research.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, indicating safe behavior. The description adds that data is 'live from a community mirror' and 'compact', providing extra context about freshness and size. 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 three sentences, uses natural language with example queries, and avoids unnecessary details. Every sentence adds value: purpose, output, and source. Front-loaded with the key action.

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

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

Given zero parameters and no output schema, the description fully explains what the tool returns and its source. The agent can accurately predict results 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?

There are zero parameters, and the input schema is fully covered (100% coverage). The description compensates by explaining the output fields (active train count, train numbers, worst delay) and overall behavior, which is sufficient for agent understanding.

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

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

The description clearly states it provides a summary of all currently active Amtrak trains grouped by route, with example queries. It differentiates from sibling tools like amtrak_station_board (station-specific) and amtrak_train_status (individual train) by focusing on a national system overview.

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

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

The description includes example queries ('how many Amtrak trains are running right now', 'which Amtrak routes have delays') which imply usage context. It does not explicitly state when not to use it or compare to siblings, but the purpose is clear enough for an agent to infer appropriate scenarios.

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 safety profile (readOnly, idempotent, non-destructive). Description adds that it's a 'live community mirror' and returns trains 'currently en route' with specific fields like delay and status. No contradictions.

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

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

Three sentences, front-loaded with purpose. Every sentence adds value. 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?

No output schema, but description explains return fields (route, scheduled vs estimated, delay, status) and provides an example call. Adequate for a read-only tool with good annotations.

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

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

Schema coverage is 100%, so baseline is 3. Description adds value by clarifying station accepts both code and name, giving examples, and explaining limit range (1-15, default 15) which is not in schema.

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

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

Description clearly states it's a station departures/arrivals board, gives example queries, and explains what it returns. Distinguishes from siblings like amtrak_train_status by focusing on station-level upcoming trains.

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

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

Explicitly says when to use it (upcoming trains at a station) and provides query examples. Implicitly excludes single train lookups or station info, which are handled by sibling tools.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds significant behavioral context: it returns station name, code, city/state, address, timezone, coordinates, and inbound train count. No contradiction with annotations.

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

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

Two concise sentences plus an example call. Every sentence adds essential information. Perfectly front-loaded with the tool's purpose.

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

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

For a simple lookup tool with one parameter and no output schema, the description fully covers what the tool returns (station name, code, address, etc.) and how to invoke it. No gaps.

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

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

The single parameter 'station' is fully described in the schema (station code or city/name). The description reinforces this with concrete examples ('Denver', 'NYP') and query patterns, adding value beyond the schema's property 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 specifies the tool performs Amtrak station lookup by code or name and lists the fields returned (station name, code, city/state, address, timezone, coordinates, inbound train count). This clearly distinguishes it from sibling tools like amtrak_station_board or amtrak_train_status.

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

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

The description includes natural language query examples like 'Where is the Amtrak station in Denver?' and 'what is station code NYP', which imply typical usage contexts. However, it does not explicitly state when to use this tool versus alternatives such as amtrak_station_board.

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, non-destructive. Description adds valuable context: data is a community mirror updating every few minutes, and returns active instances. No contradiction.

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

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

Single paragraph is well-structured: starts with purpose, gives usage examples, describes output, notes data source, and ends with example. Every sentence earns its place.

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

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

For a tool with one parameter and no output schema, the description sufficiently covers input, output, and behavior. Minor omission: no mention of handling non-existent trains or future schedules.

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

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

Schema coverage is 100%, but description adds examples, clarifies Via Rail and Brightline compatibility, and explains the parameter meaning beyond the schema's description.

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

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

Description clearly states it provides live Amtrak train status and GPS tracking. Uses specific verbs like 'returns' and 'accepts', and distinguishes from sibling tools by focusing on train-level tracking rather than routes or stations.

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

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

Provides explicit use cases ('where is my Amtrak train', 'is train 6 late') and explains input types (train number or route name). Does not explicitly state when not to use, but the specificity makes it clear.

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

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

Beyond the annotations (read-only, open-world, idempotent), the description discloses that the tool routes queries, aggregates across thousands of tools, fills arguments, returns stable citation URIs, works on every tier, and handles breaking news via live news feeds. This adds concrete behavioral expectations and does not contradict annotations.

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

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

The description is long but efficiently front-loaded with the key directive ('PREFER OVER WEB SEARCH') and organized into domains, mechanics, usage triggers, examples, default status, and alternatives. Every sentence contributes decision-relevant information without 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 tool of this complexity—acting as a meta-router with no output schema—the description covers purpose, scope, examples, escalation paths, and result format (citations). It provides enough context for the agent to use it correctly and know when to step up to more specialized tools.

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 documents the question parameter and its aliases completely (coverage 100%). The description adds examples of valid question types and trigger phrasing, which helps the agent formulate queries. However, the additional value is modest since the schema examples already convey the parameter shape, so it does not fully warrant the maximum score.

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 defines the tool as a router that answers factual questions by selecting from 5,432 tools across 1,411 sources and returning structured answers with citation URIs. It clearly distinguishes the tool from siblings like ask_pipeworx_grounded and deep_research, and from web search, with a specific verb+resource framing.

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 to prefer this over web search for factual questions, lists trigger phrases ('what is', 'look up'), gives examples, declares it as the default entry point, and names specific alternatives (ask_pipeworx_grounded, deep_research) for specific needs. This goes beyond vague guidance to directly instruct the agent on when and when not to use the tool.

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

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

Beyond the annotations (readOnlyHint, idempotentHint, etc.), the description discloses that it is an experimental edge with candidate routing improvements that may be enabled live, that no candidate is currently active (with a specific retirement date), and that it is a full working router with no fallback behavior. This provides valuable context about its state and potential variability that annotations do not cover.

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

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

The description is four sentences long and front-loads the key point ('Beta version of ask_pipeworx'). Each sentence adds information, though the specific retirement date ('2026-07-26') is somewhat granular and could be omitted, overall it remains appropriately sized and structured.

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

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

The description covers purpose, usage, behavioral state, and relationship to the stable router. It even addresses the absence of an output schema by stating the response shape matches ask_pipeworx. Given the tool's moderate complexity and the richness of the annotations and schema, this description is fully contextual and leaves no critical gaps.

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

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

The input schema provides 100% coverage with descriptions for all six parameters, including aliases for 'question'. The description only says 'same arguments' without adding any detail beyond what the schema already documents. Thus, it meets the baseline for schema-covered parameters but does not add meaningful parameter semantics beyond the schema.

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

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

The description clearly states it is a 'Beta version of ask_pipeworx: identical universal router' with 5,432 tools, same arguments, and same response shape. This specific verb ('ask') and resource ('router') clearly conveys its function as a question-routing tool, and it distinguishes itself from sibling tools like ask_pipeworx and ask_pipeworx_grounded by emphasizing its beta/experimental nature.

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

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

The description provides explicit usage guidance: 'Use it exactly like ask_pipeworx when you want the newest routing; results are compared against the stable router to decide what merges.' This tells the agent exactly when to select this tool over the stable version and implies the exclusion of using it when stable, production-grade routing is desired.

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 substantial behavioral detail beyond the annotations: explains refusal reasons (not_in_source, no_tool_match, etc.), return shape with evidence field, and the extra LLM call cost. The annotations already indicate read-only/idempotent, so this description augments with operational specifics.

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 every sentence carries useful information: purpose, routing, return format, refusal reasons, use cases, and cost. It is front-loaded with the core purpose and well-structured, though slightly verbose.

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 provides a complete picture: return schema, refusal scenarios, use cases, cost, and relation to sibling ask_pipeworx. Enough for an agent to select and invoke correctly.

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

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

Schema coverage is 100% with all parameters being aliases for 'question' and clearly described. The description adds no new parameter semantics, but the schema fully documents the sole required input. Baseline 3 is justified.

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

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

Clearly identifies the tool as a hallucination-resistant answer mode for high-stakes reads. It specifies the routing behavior (same as ask_pipeworx) and the key distinction: extracting answers only from tool results. This distinguishes it from sibling tools like ask_pipeworx.

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

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

Explicitly states when to use (quoted, cited, or acted-on answers) and when not to (casual lookups, where ask_pipeworx is preferred). Mentions the cost tradeoff (one extra LLM call) and provides an alternative tool name.

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

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

The description discloses extensive behavioral details beyond annotations: market resolution, classifier fan-out, response shapes, resolver contract (match confidence, alternatives), parent event extractor, news fallback, safety mechanisms (low-confidence, closed markets, wide spread), and resolution-rule risk. All annotations are consistent, and no contradiction exists. This level of transparency is exceptional.

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

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

While every sentence adds value, the description is extremely verbose (over 500 words in a single paragraph). It lacks clear section breaks or bullet points, making it harder to parse quickly. It could be restructured for better scannability without losing content.

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 classification types, fan-out patterns, safety checks, resolver contracts), the description covers all essential aspects. Even without an output schema, it describes response shapes, edge cases, and blocking conditions. It is fully complete for an agent to understand the tool's behavior.

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

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

Schema coverage is 100%, but the description adds significant meaning: it explains the three allowed input formats for 'market', the 'depth' enum with defaults, and 'include_raw' with use cases. This goes well beyond the schema descriptions, providing actionable context for parameter usage.

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

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

The description clearly states the tool's purpose: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It specifies inputs (slug, URL, question text) and output (evidence packet + market-vs-model comparison). The verb 'research' and resource 'Polymarket bet' are specific, and the purpose is well-distinguished from sibling tools like polymarket_edges.

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

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

The description explicitly states when to use: 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z".' It provides context but does not mention when not to use or alternative tools for similar tasks. This is clear guidance, lacking only 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 readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds context about handling off-calendar fiscal years correctly (e.g., AAPL Sep, NVDA Jan) and results sorted by primary metric, which goes beyond the annotations. No contradictions.

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

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

The description is somewhat lengthy but well-structured, front-loading with common usage phrases and key instructions. Every sentence adds value, though it could be slightly more concise without losing critical information.

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

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

Given the tool's complexity, the description fully covers what the agent needs to select and invoke it correctly: entity types, input formats, data sources, return structure (paired data + citation URIs), and sorting behavior. No output schema is present, so the description adequately explains return values.

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

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

Schema coverage is 100%, but the description significantly enhances parameter meaning by explaining the enum values ('company' vs 'drug') with concrete examples of valid inputs (tickers or drug names) and what data each retrieves. This is highly informative 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 explicitly states the tool performs side-by-side comparisons of 2–5 companies or drugs, with specific example phrases like 'compare X and Y' and 'head to head'. It clearly distinguishes the two entity types and what data is retrieved for each, making the purpose unambiguous.

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

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

The description explicitly says 'ALWAYS PREFER over sequential single-pack lookups when comparing entities', providing a strong usage guideline. It also implicitly tells when to use company vs drug type via the examples. However, it does not explicitly state when not to use the tool, which prevents a higher score.

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

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

Annotations already declare readOnlyHint/openWorldHint, but the description goes far beyond by disclosing the internal mechanics: parallel routing, facets, gaps[] that are never invented, contradictions[], hop fields, semantic excerpting (not head-truncation), latency expectations, and the fact that current-news topics return mostly empty gaps[]. This is substantial behavioral context beyond what annotations supply.

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 (~250 words) but packed with necessary operational details. It front-loads the account requirement instead of the core purpose, slightly hurting quick scanning, but nearly every sentence earns its place by providing non-obvious information. No tautology or redundancy with the schema.

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

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

Given the tool's complexity, two parameters, and no output schema, the description is impressively complete. It specifies the return format (findings packet, verbatim evidence, confidence, source, fetched_at, citation), gaps[], contradictions[], hop field, and even covers edge cases like signed-out usage and breaking news topics. It does not rely on the output schema because none exists.

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: it explains what each depth level does (quick=3 facets single hop, standard=5 with gap recovery + contradictions, thorough=8 with iterative hop), and clarifies that 'question' can be broad/multi-part. This enriches understanding beyond the schema's bare 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 unambiguously states the tool's function: 'Grounded multi-source research across Pipeworx's 1411 STRUCTURED data sources... in ONE call.' It uses a specific verb (research), names the resource (structured data sources), and clearly distinguishes itself from siblings like ask_pipeworx by noting 'this is NOT open-web search' and contrasting 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?

Explicit usage guidance is provided: 'Best for broad/multi-part questions over structured data', with clear alternatives: 'For a single lookup use ask_pipeworx' and 'For BREAKING or colloquial CURRENT-NEWS... prefer ask_pipeworx'. It also specifies the account prerequisite and says to use ask_pipeworx if not signed in.

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

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

Annotations declare readOnlyHint=true and idempotentHint=true; the description adds that the tool returns 'top-N most relevant tools with names, descriptions, and full input schemas' ready to call. No contradictions.

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

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

The description is front-loaded with the core purpose and then elaborates. It includes examples and usage guidance concisely, though it could be slightly tighter without losing value.

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

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

Given the tool's complexity and the absence of an output schema, the description provides sufficient context about what is returned (top-N tools with schemas). It covers when to use and the range of data sources.

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 description adds minimal extra meaning. It provides examples of valid queries, but the schema already documents all parameters including aliases. 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 'Find tools by describing the data or task' and enumerates specific domains (SEC filings, FDA drugs, etc.). It distinguishes itself from siblings by being the meta-tool for discovery.

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

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

The description explicitly says 'Call this FIRST when you have many tools' and implies it's for browsing options, not getting a single answer. While it doesn't list exclusions, the context is clear.

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

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

Annotations indicate read-only, idempotent, non-destructive, open-world. Description adds value by noting parallel fan-out across multiple sources, constraint that only US public companies are supported, and the USPTO API soft-fail scenario. No contradictions.

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

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

Description is somewhat long but highly informative, front-loaded with examples and purpose. Every sentence adds value, though minor redundancy exists (repeats 'names not supported' in two places).

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?

Even without output schema, description details return structure: cik, company_name, recent_filings with URIs, fundamentals sorted by period_end, patent status, news sources, LEI. Also covers edge cases like patent soft-fail and required input format.

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

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

Schema coverage is 100% (both type and value described). Description adds context: value can be ticker or CIK, names not supported, and explains the 'type' enum is limited to 'company'. Meaningfully supplements schema.

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

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

Description clearly states the tool provides a 'full cross-source profile of a US public company in ONE parallel call' and lists specific data sources (SEC, XBRL, USPTO, news, GLEIF) and return fields. Distinguishes from siblings like resolve_entity and compare_entities.

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 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups' for holistic views, and advises using resolve_entity first if only a name is available. Clear when to use and when not.

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

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

Annotations already convey destructiveHint=true and idempotentHint=true. The description adds no new behavioral traits beyond restating the delete action, but it aligns with annotations without contradiction.

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

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

Two concise sentences, no wasted words. First sentence states action, second provides usage guidance. Efficient and well-structured.

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

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

For a simple single-parameter tool with full schema coverage and annotations, the description covers purpose and usage completely. No output schema needed.

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

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

Schema coverage is 100% with a clear description of 'Memory key to delete'. The description's 'by key' adds no additional semantic value beyond the schema.

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

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

The description states 'Delete a previously stored memory by key' with a specific verb and resource. It distinguishes itself from siblings 'remember' and 'recall', making the purpose 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?

The description provides explicit context for use: when context is stale, task done, or clearing sensitive data. It also mentions pairing with siblings, though it lacks explicit when-not-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?

Discloses key behaviors: 'Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format.' This adds context beyond annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint) by explaining the process and output. No contradictions.

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

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

Two sentences with no filler. The first sentence clearly states the tool's purpose and scope, and the second provides usage examples. Every word earns its place.

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

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

Given the tool's low complexity (2 simple params, no output schema), the description plus annotations fully cover what an agent needs: purpose, behavior, output format, and usage context.

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

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

Schema coverage is 100%, so baseline 3 applies. The description does not add meaning beyond what the schema provides—both 'url' and 'max_links' are already well-documented with defaults and constraints in the schema.

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

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

Description clearly states 'Generate a production-ready llms.txt file for any URL', specifying verb and resource. It differentiates from siblings by focusing specifically on llms.txt generation, while related tools like ai_visibility_check and scan_competitor_ai_presence cover broader AI visibility tasks.

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

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

Provides explicit use cases: 'getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.' No explicit when-not-to-use or alternatives, but the guidance is clear enough for typical scenarios.

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

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

Annotations already provide readOnlyHint and destructiveHint. Description adds that it returns specific fields and defaults to active subscriptions, which adds value beyond annotations. No contradiction.

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

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

Two sentences, no wasted words. Returns fields and usage suggestion are front-loaded.

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

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

Simple tool with zero required params and no output schema; description covers purpose, return fields, and usage. Complete for 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 a single boolean parameter described. Description mentions active subscriptions but doesn't add new info beyond schema. Baseline 3 is appropriate.

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

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

Clearly states 'List the caller's active subscriptions' and lists return fields. Distinguishes from sibling tools subscribe/unsubscribe.

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

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

Explicitly says when to use: 'review what you're monitoring before adding more or to find an id to cancel.' Doesn't specify when not to use, but context is clear.

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

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

The description discloses important behavioral traits not visible in annotations: rate-limited to 5 per identifier per day, free, does not count against tool-call quota, and that submissions are read daily and affect roadmap. This goes well beyond the all-false annotations, providing critical operational context for an LLM 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 relatively long, but every sentence earns its place by clarifying scope, use cases, exclusions, and constraints. It is front-loaded with the core purpose and then layers on necessary guidance without unnecessary 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 feedback submission tool with no output schema, this description is fully complete. It covers what to submit, when to submit, when NOT to submit, how to frame the message, rate limits, quota impact, and even the team's response cadence. There are no obvious gaps.

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

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

The schema already covers 100% of parameters, including type enum semantics and message guidance. The description adds extra value by instructing users to describe issues 'in terms of Pipeworx tools/packs' and not paste the end-user's prompt, which clarifies how to fill the message field effectively. This elevates it above the baseline 3.

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

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

The description opens with a clear verb+resource: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' This explicitly defines the tool's purpose and differentiates it from sibling tools like ask_pipeworx or discover_tools, which are for querying or exploring, not for submitting feedback.

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

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

The description explicitly lists when to use the tool (bug, feature/data_gap, praise) and provides a strong exclusion: if the tool came from a different MCP server, file it there instead. It also gives a disambiguation hint ('Not sure? Pipeworx tool names are the ones this connection lists'), making it clear when this tool is appropriate versus alternatives.

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

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

Annotations already indicate readOnly, openWorld, idempotent, and non-destructive hints. The description adds valuable behavioral context: it is self-aggregating, derived from CF analytics-engine, contains no PII, and is cached for 5min-1h depending on window. No contradictions with annotations.

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

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

The description is concise with only four sentences, each adding value. It front-loads the core purpose and then provides use cases and implementation details. No wasted words.

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

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

For a simple tool with one optional parameter and no output schema, the description covers everything: what it returns, how windows affect results, appropriate use cases, data provenance, and caching behavior. It is complete and self-contained.

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

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

Schema description coverage is 100% and the schema parameter description explains the enum values. The tool description enhances this by explaining the semantics of different window choices (shorter vs longer windows) and their practical implications for surfacing hot vs steady-state trends.

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

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

The description clearly states that the tool returns top tools, packs, and total call volume over recent windows. It specifies the verb 'returns' and the resource scope, distinguishing it from sibling tools that focus on specific domains like Amtrak or Polymarket.

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?

Three explicit use cases are given: discovering hot data sources, confirming canonical choices, and aligning use cases. The description also explains that shorter windows surface current trends while longer windows show steady-state demand. It does not explicitly list when not to use, but the use cases are clear enough.

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

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

Annotations indicate readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds substantial behavioral context: monotonicity checks, partition-sum verification, semantic anchor, partition filter, and fill check with live CLOB depth. It explains when a trade should not be executed (realizable edge <= 0). All consistent 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 detailed and covers all modes, checks, and edge cases. It is front-loaded with the main purpose. While every sentence adds value, the length could be slightly reduced for quicker scanning. Still well-structured.

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

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

Despite no output schema, the description fully explains the response structure (opportunities array with fields, partition_check object with fields) and provides context on fill check and custom sizing. An agent has sufficient information to understand inputs, behavior, and outputs.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds significant extra meaning, explaining how each parameter is used (e.g., event slug walking child markets, topic as seed question for cross-event scanning). This exceeds baseline 3.

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

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

The description clearly states the tool finds arbitrage opportunities via monotonicity violations and partition-sum checks. It distinguishes itself from siblings like polymarket_edges and polymarket_fill_risk by focusing on arbitrage detection using specific mathematical methods.

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 call with NO args, 'event' for specific markets, and 'topic' for cross-event scans. It recommends 'event' for specific markets and explains the use case for each mode, but does not explicitly state when not to use the tool.

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

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

Beyond annotations (readOnly, idempotent, non-destructive), the description details cache behavior (1h KV-level), edge calculation methodology, slippage treatment, and response structure including diagnostics. It fully discloses model families, segmentation, and why fed bets are excluded. 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 excessively long and dense with technical jargon (e.g., 'lognormal barrier from 90d FRED log-returns'), which may overwhelm agents. While structured into sections, it lacks conciseness and front-loading of key points.

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

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

Given the complexity of 9 parameters, three model families, and no output schema, the description is remarkably complete. It explains edge calculation segments, diagnostics for empty segments, and cache policy, leaving minimal ambiguity 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?

All 9 parameters have descriptions in the input schema (100% coverage), so the description adds limited value for individual parameters. It provides a paragraph on 'tradeable-edge knobs' but does not explain each parameter beyond what the schema already offers. Baseline 3 is appropriate.

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

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

The description explicitly states 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price', identifying a specific verb and resource. It clearly distinguishes its purpose from sibling tools by focusing on edge discovery for daily betting decisions.

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

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

The description implies usage for daily opportunity discovery and provides detailed knobs for tuning, but does not explicitly compare with sibling tools like polymarket_arbitrage or edge_tracker, nor state when not to use it. The context is clear but lacks exclusion criteria.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds valuable context: it reads snapshots, returns tracked/expired opportunities with time-series, trend computation, and limitations (60-day TTL, not intraday). 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 dense but well-structured: purpose sentence, parameter section, detailed response breakdown, and limitations. Every sentence adds value; no redundancy. Front-loaded with key 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?

Despite no output schema, the description thoroughly explains return fields (tracked[], expired[], snapshot_dates[]) with sub-fields (trend, decay_pp_per_day, lifespan_days). Limits and data gaps are noted. Complete for a complex tool.

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

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

Schema coverage is 100%, but the description adds meaningful context: default values (days=14, window='1wk'), max lookback (30), and what 'window' refers to (snapshot family). This exceeds the schema alone.

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

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

The description clearly states the tool provides 'edge persistence and decay telemetry' from daily snapshots, answering a specific question about edge longevity. It distinguishes itself from siblings like polymarket_edges by focusing on time-series behavior rather than 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 implies usage context (e.g., distinguishing fresh vs old edges) but does not explicitly list when to use or not use this tool. It provides clear context but lacks explicit exclusion criteria or alternative tool names.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds rich context: walks the ladder, returns specific metrics like slippage and verdict, and highlights risks like thin legs and forced directional risk. 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 fairly long but well-structured: summary, requirements, single-market details, basket details, and usage guidance. Every sentence is informative and earns its place, though it could be slightly more concise.

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

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

Despite no output schema, the description thoroughly explains return fields for both modes (top_of_book, vwap_fill_price, slippage_pp, etc. for single-market; theoretical_sum, realizable_sum, capture_ratio, etc. for basket). It covers edge cases like partial fills and forced directional risk, meeting the tool's complexity.

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

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

Schema coverage is 100%, with descriptions for all 4 parameters. The description adds value by explaining mode-specific behavior (e.g., size_usd interpretation differs for single-market vs basket), default values, and the auto-detection logic for basket side.

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: checking realizable-vs-theoretical edge against live CLOB order-book depth. It distinguishes between single-market and basket modes, and specifies the return fields. This differentiates it from sibling tools like polymarket_arbitrage and polymarket_edges.

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

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

Explicitly tells when to use: before acting on polymarket_arbitrage signals or polymarket_edges trades above ~$500. It also warns about risks of partial fills converting arb into directional positions, effectively guiding against misuse.

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, openWorld, idempotent, non-destructive. The description adds rich behavioral context: two operation modes, response structure with leg-by-leg prices and matched spreads, safety fields with specific conditions for compatibility_warning, temporal_alignment, and skipped counters. 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 well-organized with clear sections (TWO MODES, RESPONSE, SAFETY FIELDS) and front-loaded purpose. It is slightly verbose, particularly the final caveat about pre-mapped topics, but every sentence provides necessary information for correct tool usage.

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

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

Given the complexity of the tool (multiple modes, cross-venue, safety checks), and the absence of an output schema, the description is highly comprehensive. It covers all aspects: mode selection, response format, safety flags, edge cases, and temporal considerations, enabling an AI agent to use the tool correctly.

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

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

Schema coverage is 100%, but the description adds significant value beyond schema by explaining the behavior of each parameter, including how explicit tickers override topic mappings, listing the ten topic shortcuts, and providing examples. It clarifies when topic may not yield tradeable spreads.

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

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

The description clearly states the tool computes cross-venue spread between Kalshi and Polymarket for the same resolving question. It specifies the two modes (topic shortcuts and explicit tickers) and distinguishes itself from sibling tools like polymorph_arbitrage by focusing on cross-venue comparison.

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

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

The description explains when to use the tool and provides detailed guidance on safety fields and conditions for meaningful spreads (e.g., temporal alignment, compatibility_warning). It warns that most pre-mapped topics currently return warnings, setting expectations. It could explicitly mention alternatives but the context is clear.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds scope (scoped to identifier) and dual functionality, but does not significantly expand beyond annotation 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?

Three well-structured sentences with front-loaded action, no unnecessary words.

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

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

For a simple tool with one optional parameter and no output schema, the description covers purpose, usage context, scope, and pairing, leaving no gaps.

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

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

Schema coverage is 100%, and the description repeats the schema's info that omitting key lists all keys, adding no new semantic value beyond the schema.

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

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

The description clearly states the tool retrieves a saved value or lists all keys, with explicit verb-resource pairing and differentiation from siblings remember and forget.

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

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

The description explains when to use the tool (look up stored context) and pairs it with remember and forget, but does not explicitly state when not to use 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?

The description contradicts annotations by describing a mutation (mark_read:true flags events as read) while annotations declare readOnlyHint=true, indicating no state modification. This is a critical inconsistency.

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

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

The description is relatively concise, with the first sentence establishing purpose. It includes necessary details but could be more structured (e.g., bullet points). No wasted sentences.

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 return fields (source, citation_uri, payload), filtering options, and the mark_read behavior. Without an output schema, it adequately explains what the tool returns, though the payload structure is not detailed.

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

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

With 100% schema coverage, the description adds meaningful context: it explains filtering by type with an example (sec_8k), using since with ISO timestamps, and the effect of mark_read. This goes beyond the schema's parameter descriptions.

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

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

The description clearly states the tool retrieves fired events from a subscription feed, specifying it returns recent alerts with source, citation_uri, and raw payload. However, it does not explicitly distinguish this tool from sibling tools, which include many unrelated ones.

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 mentions polling works fine and provides an alternative endpoint, but it lacks explicit guidance on when to use this tool versus alternatives or when not to use it. Usage context is implied but not directly stated.

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, openWorld, idempotent, non-destructive. The description adds context: fans out to multiple sources, fallback logic, soft-fail for USPTO, returns grouped changes with citation URIs. Slightly more detail on rate limits would enhance, but still strong.

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

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

The description is compact but information-dense, starting with example queries, then purpose, sources, parameter details, and ending with sibling guidance. Every sentence contributes value without waste.

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

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

Given 3 parameters, 100% schema coverage, no output schema, and complex multi-source aggregation, the description covers purpose, usage context, expected sources, fallback behavior, and output structure (changes grouped by source, total count, citation URIs). Complete for the use case.

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

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

Schema coverage is 100%, but description adds examples for `since` ('7d', '30d', '3m', '1y') and suggests typical monitoring values. It clarifies `value` accepts ticker or CIK, and `type` is only 'company'. Adds significant value beyond schema.

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

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

The description explicitly states it provides a 'change feed for a company in the last N days/weeks/months in ONE parallel call,' gives example queries, and lists data sources. It distinguishes from the sibling 'entity_profile' by clarifying when to use the alternative.

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 guidance: use for dynamic changes over a window, and explicitly says to use entity_profile for static profiles. It also explains fallback behavior (GDELT→GNews) and soft-failures for USPTO.

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

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

Description adds key behavioral details not in annotations: scoped by identifier, persistence differences between authenticated (persistent) and anonymous (24-hour) sessions, and idempotent nature implied by 'save' – no contradiction.

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

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

Three sentences with no fluff, front-loaded with purpose, then usage guidance, then behavioral details. Every sentence adds value.

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

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

Given simple params, no output schema, and rich annotations (idempotentHint true), description provides all needed context: scope, persistence, pairing with recall/forget.

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; description adds naming conventions (e.g., 'subject_property') and clarifies key-value storage, going beyond schema but not required.

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

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

The description clearly states the verb 'Save' and the resource 'data the agent will need to reuse later', and distinguishes itself from sibling tools 'recall' and 'forget' by indicating pairing.

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

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

Explicitly says 'Use when you discover something worth carrying forward' and references related tools 'recall' and 'forget', but does not explicitly state when not to use 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?

Annotations already declare readOnlyHint and idempotence. Description adds that each call cascades through multiple internal endpoints, replacing 2-3 manual lookups, which is useful behavioral context.

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

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

Front-loaded with examples and structured into supported types. Slightly long but every sentence adds value; could be trimmed 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?

Covers purpose, usage, output details for two entity types, and internal behavior. No output schema, but description fully compensates. Complete for agent decision-making.

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

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

Despite 100% schema coverage, description adds significant meaning: it explains output fields (ticker, CIK, RxCUI, etc.) and citation URIs for each entity type, going well beyond the schema's property descriptions.

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

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

Description clearly states it resolves names to official identifiers with specific verbs and examples. Distinguishes itself from sibling tools by being the go-to for name-to-ID conversion.

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 FIRST whenever you have a name but need an ID.' Provides context for each entity type but does not explicitly exclude other scenarios.

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, openWorld. Description adds behavioral details: probes with ai_visibility_check, ranks by score, returns per-entity score/confidence/signal density, treats first entity as subject. No contradictions and adds context beyond annotations.

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

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

Two sentences: first states core functionality (compare, probe, rank), second gives usage example and return details. No filler, front-loaded, every sentence earns its place.

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

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

Despite no output schema, description adequately explains return format (ranked list with score, confidence, signal density). Parameter descriptions cover constraints (2-8 entities). Annotations cover safety. No major gaps identified.

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

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

Schema covers 100% of parameters with descriptions. The description adds extra meaning: first entity in 'entities' is treated as subject for narrative, default models is just workers-ai, _apiKey needed only for anthropic, context disambiguates names. This exceeds baseline 3.

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

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

The description clearly states it compares AI visibility of multiple entities side-by-side, probes each using ai_visibility_check, ranks results, and surfaces most/least recognized. It distinguishes from sibling ai_visibility_check (single entity) by emphasizing multi-entity 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?

Provides a concrete use case ('competitive AI-marketing audits') and implies usage context. Does not explicitly contrast with single-entity alternative (ai_visibility_check) but the description's reference to 'multiple entities' and 'competitors' signals appropriate scenarios.

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-safe and idempotent. Description adds valuable context: graceful degradation with latency for bundlephobia, partial failure reporting, and that other sources still return.

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

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

Description is efficient and front-loaded with purpose, then usage, then behavioral details. Slightly long but every sentence adds unique 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?

Despite no output schema, description details all return fields including summary block, per-advisory detail, links, and alternatives. Also covers edge cases like latency and partial failures.

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

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

Schema provides full descriptions for both parameters. Description adds extra value by clarifying scoped package acceptance and default behavior for version.

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

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

Description clearly states the tool performs a composite check for npm packages evaluating safety, popularity, and size with specific sources. Distinguishes from siblings by focusing on dependency scanning.

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: when agent asks about package safety/popularity/size. Also notes ecosystem limitations (NPM only) and directs users to alternative tools 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, openWorldHint, idempotentHint, and destructiveHint. The description adds significant behavioral context: the embedding model (BGE-base-en), cosine similarity over 500-char overlapping windows, a 200K char cap with truncation and flagging, and that passages include character offsets for quote verification. This exceeds the annotation coverage.

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

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

The description is concise: two sentences that immediately convey the tool's purpose, usage, and key technical details. Every sentence adds value without redundancy.

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

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

Given the tool's complexity and lack of output schema, the description covers all necessary aspects: behavioral details, parameter meanings, use case, pairing with another tool, return values (passages with offsets and scores), and limitations (cap, truncation). It is complete for an agent 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 description coverage is 100% for all three parameters. The description adds extra context beyond the schema, such as the 200K char cap (mentioned in schema too), the default limit, and natural-language query examples. It also explains the embedding model and window size, which are not in the schema.

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

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

The description clearly states the tool performs semantic search inside a fetched record, with examples like SEC 10-K body or article. It explicitly distinguishes from the sibling tool 'ask_pipeworx_grounded' by describing their complementary roles.

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 guidance on when to use the tool: 'when the record is too big to cram into the prompt'. It also suggests pairing with ask_pipeworx_grounded. While it doesn't explicitly state when not to use it, the context is sufficient.

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

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

Discloses behavioral traits beyond annotations: subscription creation returns an id, requires auth, delivery limitations (SMS cap, webhook auto-disable). No contradiction with annotations (readOnlyHint=false, idempotentHint=true). Does not mention all potential side effects, but sufficient.

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

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

Well-structured with core purpose front-loaded. Slightly lengthy due to comprehensive examples and details, but each sentence adds value. Concise for the complexity covered.

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?

Completeness is high: describes return value (subscription id), all types, parameters, delivery behaviors, and account prerequisites. No output schema, but description compensates adequately.

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

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

Adds significant meaning beyond the schema: explains the structure of params for each type with examples, details delivery options and their constraints (e.g., webhook signing). Schema coverage is 100%, but description enriches understanding.

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

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

The description clearly states the tool's action: 'Create a proactive monitoring subscription to a live-data event stream. Returns the new subscription id.' It is specific and distinguishes 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?

Provides explicit prerequisites (requires Pipeworx OAuth account) and context (anonymous/BYO cannot persist). Details when to use for proactive monitoring. Though it doesn't explicitly state when not to use, the sibling context and mention of delivery constraints offer adequate 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=true, idempotentHint=true, destructiveHint=false. The description adds valuable behavioral context: returns category-bucketed examples with exact tool+argument shapes, and draws from a live catalog. No contradiction.

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

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

The description is slightly verbose but well-structured with a clear flow: query examples, what it returns, usage guidance. Every sentence adds value; could be tightened slightly.

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 one optional parameter and no output schema, the description fully covers when to use, how to use, what to expect, and the return structure. No gaps.

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

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

Schema coverage is 100% (1 optional parameter). The description adds meaning by explaining that omitting topic gives a full spread, and lists example topics, going beyond the schema's description.

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

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

The description clearly identifies the tool as the onboarding entry point, explaining it returns category-bucketed example questions and tool shapes. It distinguishes from sibling tools like discover_tools and ask_pipeworx by specifying this is for learning what Pipeworx can do.

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

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

Explicitly states 'Use this FIRST when you do not yet know what Pipeworx can do' and explains when to pass a topic. Provides clear context for when to use versus alternatives.

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

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

Discloses key behaviors beyond annotations: ownership restriction, soft-delete (deactivation not deletion), and historical data persistence via recent_alerts.

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

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

Two concise sentences with front-loaded purpose and no extraneous information.

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

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

For a simple one-parameter mutation, description covers effect (deactivation, not deletion) and ownership. Does not address error cases, but idempotentHint mitigates.

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

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

Schema covers the single parameter with description; the tool's description adds no further parameter details. Baseline score for high schema coverage.

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

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

The description clearly states the action ('Cancel a subscription by id') and resource, distinguishing it from sibling tools like subscribe and list_subscriptions.

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

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

Explicitly mentions ownership enforcement ('you can only cancel your own subscriptions') and the deactivation behavior, providing clear context for when to use.

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

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

Annotations indicate read-only, open-world, idempotent. Description adds behavioral details: returns a verdict with specific categories, includes evidence and reasoning, and describes two internal paths (SEC/EDGAR vs. grounded pipeline). Does not contradict annotations.

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

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

Description is well-organized and front-loaded with triggers and purpose. While it packs a lot of valuable detail, it could be slightly more concise. However, every sentence adds value.

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

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

Given the complexity of claim verification, the description covers purpose, usage, internal routing, return structure, and examples. Lacks explicit mention of unsupported claim types, but it's sufficient for an agent to understand scope.

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%. Description adds meaning beyond schema: gives examples for 'claim', explains default behavior and usage tips for 'tolerance_pct' (range, override, default, and hallucination detection use-case).

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

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

Description starts with clear natural-language triggers, states the core function (factual claim verification), and distinguishes between company-financial and other claims. It clearly differentiates from sibling tools by focusing on claim verification.

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

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

Explicitly states 'Use whenever the agent needs to check whether something a user said is factually correct.' Provides context for financial vs. other claims but does not explicitly list when not to use it. Could mention alternatives like deep_research for non-factual queries.

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