Kraken

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

Annotations (readOnlyHint, openWorldHint, destructiveHint) are complemented by description detailing routing to 2,520 tools, argument filling, and structured output with citations. No contradiction; 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?

Description is lengthy but front-loaded with critical preference and use cases. It includes many examples, which add value but reduce conciseness. Overall well-structured and effective.

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

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

Given the complexity (many tools, no output schema), the description is remarkably complete: explains routing, output format (structured with citations), and provides extensive examples. Leaves little ambiguity.

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

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

Single 'question' parameter with schema coverage 100%. Description enriches meaning by specifying what constitutes a good question, though schema already provides basics. Slightly above baseline due to added context.

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

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

The description clearly states the tool is for asking factual questions about structured data, listing specific domains (SEC filings, FDA drug data, etc.) and providing numerous examples. It distinguishes itself from web search, making the purpose unambiguous.

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

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

Explicitly advises 'PREFER OVER WEB SEARCH' and gives detailed usage scenarios, including specific question types and examples. It also implies broad applicability, leaving no doubt 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?

The description adds no behavioral context beyond what annotations already provide. Annotations declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear, but the description omits any details about return format, pagination, or behavior with empty parameters.

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

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

The description is a single short phrase, but it is under-specified rather than concise. It lacks essential information and does not earn its place by conveying meaningful 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?

The tool has two parameters and no output schema, yet the description provides no guidance on how to use it. The agent cannot determine what the tool returns or how to construct a valid request.

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

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

The input schema has two parameters ('info' and 'pair') with 0% schema description coverage. The description does not explain the meaning, format, or allowed values of these parameters, leaving the agent with no guidance.

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

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

The description 'Pair info.' is a tautology that does not specify any action or resource. It fails to indicate whether the tool retrieves, lists, or searches asset pairs, and does not distinguish it from sibling tools like 'ticker' or 'trades'.

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?

No guidance is provided on when to use this tool versus alternatives. There is no mention of context, prerequisites, or scenarios where this tool is preferred over other trading-related 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 indicate the tool is read-only and non-destructive. The description adds no behavioral context beyond what annotations provide, missing opportunities to explain side effects, auth needs, or return behavior.

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

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

The description is extremely short but at the expense of completeness. It is not sufficiently informative for a tool with two parameters and no output 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 lack of output schema and low parameter documentation, the description is critically incomplete. It does not explain return values, parameter usage, or constraints.

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 0%, but the description does not clarify the meaning or format of the parameters 'asset' and 'aclass'. This leaves the agent unable to correctly populate the parameters.

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

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

The description 'Asset info.' is vague and does not specify what action the tool performs (e.g., retrieve, list, search). It fails to distinguish from siblings like asset_pairs or ticker, which likely also provide asset-related information.

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?

No guidance is provided on when to use this tool versus alternatives. The description lacks context for when the tool should be invoked, such as prerequisites or typical use cases.

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

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

Annotations already indicate read-only, open-world, non-destructive behavior. The description adds valuable context: the tool resolves markets, classifies bet types, fans out to relevant packs, and returns evidence plus comparison. No side effects are mentioned, but the description supplements annotations well.

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 typical but every sentence adds value: input types, processing steps, use cases, and product positioning. It is front-loaded with purpose and efficiently structured, though slightly verbose for a simple tool. No wasted words.

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

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

Despite no output schema, the description fully explains the return (evidence packet and market-vs-model comparison). It covers inputs, behavior, classification types, and output format. The tool is complex, but the description leaves no major gaps.

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

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

Schema coverage is 100% with descriptions for both 'market' and 'depth'. The description adds clarity by explaining that 'market' can be a slug, URL, or question text, and that 'depth' controls the number of evidence sources (quick vs. thorough). This meaningfully enhances 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 researches a Polymarket bet by pulling Pipeworx data, specifies input types (slug, URL, question text), and outlines the resolution process. It distinguishes from siblings by positioning itself as the core demo product that orchestrates data sources.

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

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

The description provides explicit use cases: 'should I bet on X?', 'what does the data say about this Polymarket market?', 'is there edge in this bet?'. It does not list alternatives but implies it should be used for comprehensive bet research rather than individual data lookups.

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

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

Annotations already mark as read-only and non-destructive. Description adds specific data sources (SEC EDGAR/XBRL, FAERS, FDA, clinicaltrials) and citation URIs, enhancing transparency.

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

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

Single paragraph covering purpose, usage, type details, and efficiency gain. Efficient and well-structured, though could be split for even clearer skimming.

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 handling two entity types with varied data sources, the description covers what is returned (paired data + URIs) and data origins, adequate despite no output schema.

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

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

Schema coverage is 100%, so baseline 3 applies. Description echoes schema details (tickers vs drug names) but adds no extra 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?

Description clearly states the tool compares 2-5 companies or drugs side by side, with specific data sources for each type. It differentiates from sibling tools by noting it replaces 8-15 sequential calls.

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

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

Provides explicit use-case examples like 'compare X and Y', 'X vs Y', and 'which is bigger'. Lacks explicit exclusions but context is clear.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds no behavioral context about what the orderbook contains (e.g., bids/asks, levels, changes over time), which would be valuable beyond annotations.

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

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

The description is extremely short, but it sacrifices clarity. It is not front-loaded with key information. A better description would be concise but informative, such as 'Retrieves orderbook depth for a trading pair with optional level count.'

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 is incomplete for basic usage. It does not explain what the tool returns (e.g., arrays of bid/ask prices and volumes) or how the parameters affect results. Given the simple concept, a one-sentence description could suffice, but this one lacks essential details.

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 0% schema description coverage, the description must compensate. It does not mention the parameters 'pair' (required, presumably the trading pair) or 'count' (optional, likely number of levels). The description provides no 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 is a single word 'Orderbook', which identifies the resource but not the action. It is vague; a specific verb like 'retrieve' or 'get' would clarify the purpose. Siblings like 'ticker' and 'spread' are in the same domain, but no differentiation is provided.

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?

No guidance on when to use this tool versus alternatives. For example, there is no mention of when to prefer 'depth' over 'spread' or 'ticker'. The description does not provide any context about the tool's role.

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

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

Annotations already indicate readOnlyHint=true and destructiveHint=false. The description adds that it returns 'top-N most relevant tools with names + descriptions', providing useful behavioral context beyond the annotations.

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

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

The description is two sentences with front-loaded purpose and usage guidance. The list of example domains is somewhat lengthy but valuable for an agent to understand scope. No redundant text.

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 simple purpose as a meta-discovery tool, the description covers use case, behavior, output (top-N tools with names+descriptions), and usage context. No output schema needed, and no missing critical information.

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

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

With 100% schema description coverage, the schema already documents both parameters. The description adds usage examples for query and implies the limit parameter via 'top-N', but does not significantly expand parameter meaning beyond the schema.

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

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

The description clearly states 'Find tools by describing the data or task' and provides a list of example domains (SEC filings, financials, etc.), distinguishing it from specific sibling tools like assets or trades.

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

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

The description explicitly advises 'Call this FIRST when you have many tools available and want to see the option set', giving clear when-to-use guidance, though it does not list when-not or alternatives beyond implying it is a first step.

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 and non-destructive. Description adds valuable context about returned data types (SEC filings, fundamentals, patents, news, LEI) and citation URIs. 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 concise (~5 sentences) and front-loaded with purpose. No fluff, though slightly verbose with examples. Effectively communicates key information.

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

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

Given no output schema, the description comprehensively lists all return components and their sources. Sibling tools are data-specific, making this aggregator's role clear and complete.

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

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

Schema already covers all parameters (100% coverage). Description adds clarity: type only 'company', value accepts ticker or CIK, and names not supported. Exceeds baseline.

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

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

The description clearly states the tool's purpose as aggregating comprehensive company data in one call, with specific examples and use cases. It distinguishes from siblings by consolidating multiple tools.

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

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

Explicitly specifies when to use (e.g., 'tell me about X', 'research Microsoft') and when not (e.g., names not supported, use resolve_entity first). Clear guidance on alternatives.

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

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

Annotations already indicate destructiveHint=true; the description adds context about clearing sensitive data and agent-saved memories, justifying deletion without contradicting annotations.

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

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

Three short sentences, each purposeful: purpose, usage guidance, and pairing suggestion. No extraneous text.

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 destructive operation with one parameter and annotations present, the description fully covers what an agent needs to know, including why and when to use it.

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

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

Input schema covers 100% of the single parameter with a description; the description does not add further semantic detail, so baseline score applies.

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

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

The description explicitly states 'Delete a previously stored memory by key' with a specific verb and resource, clearly distinguishing it from sibling tools like 'remember' and 'recall'.

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

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

Provides clear contexts for use (stale data, task completion, clearing sensitive data) and recommends pairing with 'remember' and 'recall', but omits explicit when-not-to-use or alternatives.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds no further behavioral context (e.g., return format, pagination, rate limits). No contradiction detected.

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

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

The description is extremely concise (two words) and front-loaded, but it sacrifices completeness. While it earns its place, it does not provide sufficient 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 has three parameters and no output schema, the description is critically incomplete. It does not explain parameter meanings, return values, or any behavioral details, making it inadequate for an agent to use correctly.

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

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

Schema coverage is 0%, yet the description provides no explanation for the three parameters (pair, since, interval). The description must compensate but fails entirely, leaving the agent without semantic guidance.

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

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

The description 'OHLC candles' identifies the resource (candles) but lacks a verb (e.g., 'get', 'fetch'), making the action ambiguous. Compared to siblings like 'ticker' or 'trades', there is no differentiation.

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

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

No guidance on when to use this tool versus alternatives. It does not discuss prerequisites, context, or exclusions, leaving the agent to infer usage from the name alone.

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 behavioral context beyond annotations: rate limit of 5 per identifier per day, description of how feedback is processed (digests daily, affects roadmap), and that it is free. 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 informative but slightly verbose. Each sentence is useful, but it could be tightened slightly. Front-loads key information effectively.

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

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

Given the tool's complexity (3 params, nested object, enum, no output schema), the description provides complete guidance on when and how to use the tool, including context structure and message formatting. 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%, so parameters are well-documented. The description adds semantic value by explaining how to write the message (be specific, in terms of tools/packs, avoid pasting end-user prompt).

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: sending feedback to the Pipeworx team about bugs, missing features, data gaps, or praise. It distinguishes itself from sibling tools by describing a specific use case not covered by other tools (e.g., ask_pipeworx for questions, not 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?

Explicitly states when to use the tool for each feedback type (bug, feature, data_gap, praise) and gives instructions on how to describe the issue in terms of Pipeworx tools/packs. Also mentions rate limits and that feedback is free and doesn't count against quota.

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 readOnlyHint and openWorldHint annotations, the description details the return content (ranked opportunities with reasoning) and the monotonicity-checking logic, adding significant behavioral context.

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

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

The description is well-structured, front-loaded with purpose, and each sentence provides essential information without redundancy. It efficiently covers two modes and examples.

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

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

Despite no output schema, the description explains the return format. It covers both modes, the underlying logic, and provides enough context for an agent to decide when to use the tool.

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

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

With 100% schema coverage, the baseline is 3. The description adds value by elaborating on the purpose and usage context of each parameter (e.g., explaining cross-event mode catches cases missed by single-event mode).

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, with specific modes. However, it does not explicitly distinguish from sibling tool 'polymarket_edges', so it slightly misses the top score.

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 explains when to use event vs topic mode, including a concrete example for cross-event mode. It lacks explicit 'when not to use' or alternatives, but provides clear context for each mode.

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 details the algorithm (scans top markets, groups by asset, fetches price history once, computes model probability, ranks by |edge|) and discloses it's V1 covering crypto-price bets with a lognormal model from FRED and live coinpaprika price. This goes well beyond the annotations (readOnlyHint, openWorldHint) 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?

The description is a single paragraph that front-loads the main action and then explains details. It is well-structured but somewhat verbose for a tool description; however, it remains clear and organized.

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

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

The description covers the input schema sufficiently, explains the output shape (top N ranked with trade direction), and provides context on the model and scope. Without an output schema, it compensates well, making the tool's behavior easy to understand.

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

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

Schema description coverage is 100%, so the schema already documents each parameter. The description does not add new semantic information beyond what the schema provides, leading to a baseline score of 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 scans high-volume Polymarket markets, identifies where Pipeworx data disagrees with market price, and returns ranked edges with suggested trade direction. It distinguishes itself from siblings like 'polymarket_arbitrage' by focusing on crypto-price bets and edge magnitude ranking.

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 specifies it's built for the 'what should I bet on today' question and mentions it's for crypto-price bets (V1). It implies usage context but does not explicitly state when not to use it or provide alternatives like 'bet_research' for other bet types.

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 and non-destructive; description adds scoping to an identifier and pairing context, which is useful but not beyond what annotations imply.

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

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

Three concise sentences front-loading the main purpose, followed by usage guidance and pairing, with no redundant 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 tool with one optional parameter and no output schema, the description covers purpose, usage, scoping, and relationships to siblings, making it fully complete.

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

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

Schema covers the key parameter fully; description adds the behavior of omitting key to list all keys, providing additional meaning beyond the schema.

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

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

The description clearly states the tool retrieves a value saved via remember or lists all keys when no key is provided, distinguishing it from sibling tools remember and forget.

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

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

Explicitly states when to use (look up stored context) and implicitly when not (re-deriving), and mentions scoping and pairing with remember/forget.

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

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

Annotations already indicate read-only and non-destructive. Description adds beyond: explains parallel queries to specific sources, date formats, and return structure. 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 detailed but front-loaded with purpose, each sentence adds value. Slightly long but justified by complexity.

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

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

Complete information for a tool with no output schema: explains return shape, external sources, and input parameters. Sufficient for correct invocation.

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

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

Schema coverage is 100% but description adds value: explains acceptable date formats with examples, clarifies 'type' only supports company, and specifies ticker/CIK for value.

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

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

The description clearly states the tool's purpose with a question and example queries, specifying it retrieves recent changes from multiple sources. It distinguishes from siblings by its focused functionality.

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

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

Provides numerous example user queries to guide when to use. Mentions parallel fan-out to three sources, but lacks explicit comparison to sibling tools for when to avoid.

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 behavioral details beyond annotations, such as persistence differences between authenticated and anonymous users (24 hours). However, it omits potential limits like memory count or size constraints.

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 4-sentence description front-loads purpose, includes usage guidance, and mentions companion tools. No wasted words.

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

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

Covers purpose, usage, scoping, persistence, and companions. Adequate for a simple key-value storage tool with no output schema.

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

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

Schema coverage is 100%, so the description adds minimal meaning beyond examples of key patterns. Baseline 3 is appropriate.

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

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

The description clearly states the tool saves data for reuse across conversations, using a specific verb and resource. It distinguishes from siblings like 'recall' and 'forget' by mentioning them explicitly.

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

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

Provides explicit guidance on when to use the tool (discovering something worth carrying forward) and references alternative tools (recall, forget) for complementary actions.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. Description adds that it returns citation URIs (pipeworx://). No contradictions, and adds useful behavioral context beyond annotations.

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

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

Description is concise (5 sentences), front-loaded with purpose, includes examples, and then usage guidance. 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 mentions return of IDs and citation URIs. Examples provide concrete outputs. Missing explicit format of return structure, but adequate for 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%, but description adds examples for both types and clarifies acceptable values (ticker, CIK, name for company; brand/generic for drug). This significantly enhances schema descriptions.

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

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

The description clearly states it looks up canonical/official identifiers for companies or drugs, specifying CIK, ticker, RxCUI, LEI. It distinguishes from siblings by indicating it should be used before other tools, and mentions replacing multiple lookup calls.

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

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

Explicitly states when to use (when needing IDs for other tools) and provides usage ordering. Lacks explicit when-not-to-use guidance, but context is clear.

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

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

Annotations already indicate readOnlyHint=true and destructiveHint=false, so the safety profile is clear. However, the description adds no further behavioral traits (e.g., timezone, format), which would be helpful for an agent.

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

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

The description is extremely concise, being a single sentence fragment. While it is short, it lacks structure and front-loads minimal information, which may not be fully effective for an agent.

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

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

Given no output schema, the description should explain what the tool returns (e.g., format, timezone). The phrase 'Server time.' does not provide enough context for an agent to understand the output or 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?

The input schema has no parameters, and schema description coverage is 100%. According to the rubric, zero parameters earns a baseline of 4. The description adds no extra semantic detail but is not required to.

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 'Server time.' is minimal and essentially restates the tool name without adding clarity or distinguishing it from sibling tools like 'system_status' or 'ticker' that might also relate to time.

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?

No guidance is provided on when to use this tool versus alternatives such as 'system_status' or 'trades'. The description lacks context for appropriate usage 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 readOnlyHint=true and destructiveHint=false. The description adds no behavioral context beyond stating 'Recent spread', which offers no insight into behavior, authentication, or data scope.

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

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

Extremely short but under-specified. A single vague phrase does not make for a good description; it sacrifices completeness for brevity without being useful.

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

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

Lacks critical information such as what data is returned (e.g., spread values, timestamps), how results are structured, or any edge cases. Incomplete for a tool with no output schema.

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

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

With 0% schema description coverage and two parameters (pair, since), the description provides no explanation. 'pair' and 'since' are not defined, leaving the agent uninformed about their meaning or format.

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 'Recent spread.' is vague and fails to clearly state what the tool does. It merely restates the tool name with 'Recent' and does not specify a verb or the resource being acted upon.

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?

No guidance on when to use this tool vs alternatives like 'depth', 'ticker', or 'trades'. The description lacks any context about appropriate use cases.

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

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

Annotations already indicate readOnlyHint=true and destructiveHint=false, but the description adds no behavioral context beyond 'status'. It does not disclose what changes are observed or any side effects.

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 only two words, which is under-specified rather than concise. It does not form a complete sentence or provide sufficient information to earn 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 has no input schema, no output schema, and good annotations, the description is still too sparse. An agent needs to understand what 'Exchange status' entails, which is not provided.

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

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

The input schema has no parameters, so schema description coverage is 100%. With zero parameters, the description need not explain inputs; the baseline of 4 applies. However, the description is minimal.

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 'Exchange status' is vague. It does not specify what kind of status (e.g., system health, operation status, market status) or what the tool returns. It fails to differentiate from sibling tools like server_time or depth.

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?

No guidance is provided on when to use this tool versus alternatives. The description does not mention any context, prerequisites, or 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?

While annotations correctly mark it as read-only and non-destructive, the description adds no behavioral context beyond the name. It does not explain what data the ticker returns or how often it updates, leaving the agent with limited understanding of the tool's behavior.

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

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

At only two words, the description is under-specified rather than concise. It sacrifices essential details for brevity, making it insufficient for an agent to understand the tool's purpose and 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 abundance of sibling tools, the lack of output schema, and the single parameter, the description is entirely inadequate. It fails to provide even minimal context to differentiate 'ticker' from its peers or to guide effective use.

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

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

The schema has 0% description coverage, and the description does not clarify the 'pair' parameter. There is no indication of the expected format (e.g., 'XBTUSD' vs 'BTC-USD') or possible values, severely impairing correct input construction.

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 'Current ticker.' is extremely vague. It does not specify what a ticker entails (e.g., last price, volume, bid/ask). Moreover, it fails to differentiate from sibling tools like 'ohlc' or 'trades' which also provide market data.

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

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

No guidance is provided on when to use this tool versus alternatives such as 'asset_pairs', 'depth', or 'trades'. An agent has no basis to select this tool over others for getting current market data.

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

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

Annotations already indicate readOnlyHint=true and destructiveHint=false, so the safety profile is clear. However, the description adds no behavioral context beyond that (e.g., rate limits, historical depth, or output format).

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

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

The description is extremely short at two words, but it is under-specified rather than concise. It fails to provide essential information in a compact form.

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 (3 parameters, no output schema, multiple sibling tools), the description is severely incomplete. It does not explain what 'recent trades' means, how results are ordered, or how it relates to other 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?

With 0% schema description coverage, the description must compensate but it provides no information about the parameters (pair, count, since). The required 'pair' parameter's format is not hinted, and optional parameters 'count' and 'since' are entirely unexplained.

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 'Recent trades.' vaguely indicates the tool returns recent trade data, but it does not specify the scope (e.g., by trading pair) or differentiate it from siblings like ticker (price), depth (order book), or ohlc (candlesticks). It adds minimal value over the tool's name.

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?

No guidance is provided on when to use this tool versus alternatives such as ticker, depth, or ohlc. There is no mention of prerequisites, limitations, or context for appropriate use.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds behavioral context: it returns a verdict, extracted structured form, actual value with citation, and percent delta. It also explains the domain limitation and that it combines multiple steps. 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 informative and well-structured, providing purpose, usage, and output details. It is slightly verbose but each sentence adds value, so it earns a 4.

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 (fact-checking with multiple outputs) and the absence of an output schema, the description fully explains what the tool does, its domain limitations, and its return structure. It is complete and leaves no ambiguity.

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% for the single parameter 'claim'. The description adds meaning beyond the schema by providing specific examples ('Apple's FY2024 revenue was $400 billion') and clarifying it takes natural-language claims.

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 (fact-check, verify, validate) and the specific resource (natural-language factual claim). It distinguishes itself by specifying the domain (company-financial claims via SEC EDGAR + XBRL) and noting it replaces multiple sequential calls, differentiating it from siblings.

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

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

The description explicitly tells when to use the tool ('Use when an agent needs to check whether something a user said is true') and provides example queries. It does not mention alternatives, but the domain is narrow enough that it's clear when to use this over other tools.

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