Opendatasoft

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

Annotations already indicate readOnly, openWorld, and non-destructive behavior. The description adds meaningful context: it explains that the tool routes to vetted sources, fills arguments, and returns citations with stable URIs. This complements the 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?

The description is a single focused paragraph that front-loads the key guidance (PREFER OVER WEB SEARCH) and provides ample examples. It is concise without being terse, though bullet points could improve scannability.

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 a single parameter and no output schema, the description provides sufficient context: it explains what kinds of questions are suitable, the breadth of sources, and the type of output (structured answer with citations). It does not detail output format but that is acceptable for a meta-router.

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

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

The only parameter (question) is fully described in the schema with 'Your question or request in natural language', which is sufficient. The description reiterates this implicitly through examples but adds no new parameter-level details. Baseline 3 is appropriate given 100% 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 tool's purpose: it is a meta-search tool that routes factual questions to 2,520 tools across 575 sources, returning structured answers with citations. It explicitly contrasts with web search and lists many domains (SEC filings, FDA data, etc.), making it distinct from sibling tools like entity_profile or dataset.

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 to prefer this tool over web search for factual questions and provides specific query examples and trigger phrases ("what is", "look up", etc.). It does not explicitly state when not to use it, but the positive guidance is very clear and directive.

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, non-destructive. The description confirms read-only behavior and adds detail on internal fan-out logic and classification, for example citing specific packs for different bet types. No contradictions; adds value beyond annotations.

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

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

The description is moderately long but front-loaded with purpose and input types. Every sentence adds information, though the meta comment about demo product could be seen as slightly extraneous. Overall efficient.

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

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

Despite no output schema, the description sufficiently explains return structure (evidence packet + market-vs-model comparison) and internal processes (resolve market, classify bet, fan-out). Covers tool's complexity well for an agent.

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

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

Schema coverage is 100%, but the description enhances understanding: it elaborates on the 'market' parameter's three input forms and clarifies the 'depth' parameter (quick vs thorough) beyond the enum labels. This adds practical usage 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 identifies the tool's purpose: researching Polymarket bets by pulling Pipeworx data. It specifies input types (slug, URL, question text) and outputs (evidence packet, market-vs-model comparison), distinguishing it from siblings like 'polymarket_arbitrage' which focuses on arbitrage.

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

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

Provides explicit use cases ('should I bet on X?', 'what does the data say?', 'is there edge?') and states this is the core demo product, implying it should be preferred for bet research. However, it does not explicitly exclude cases where other tools like 'validate_claim' might be more appropriate.

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

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

Aligns with annotations (readOnlyHint, non-destructive). Discloses specific data pulled for each entity type and mentions citation URIs, adding value beyond annotations.

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

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

Concise yet comprehensive. Front-loads core purpose, then details usage and data sources. Every sentence adds distinct 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?

Covers key aspects: entity types, data sources, return format, and efficiency. Lacks output schema but mentions paired data and citations, sufficient for agent invocation.

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

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

Schema coverage is 100% with good descriptions. The description adds contextual examples (tickers, drug names) and clarifies the format of values.

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

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

Clearly states it compares 2-5 companies or drugs side by side, with specific data sources for each type. Distinguishes from sibling tools like entity_profile by focusing on 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?

Explicitly lists trigger phrases and use cases. Implies efficiency over sequential calls but doesn't explicitly state when not to use or name exact alternatives.

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

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

Annotations already indicate readOnlyHint=true, openWorldHint=true, destructiveHint=false, so the base behavioral profile is covered. However, the description does not add any additional behavioral context, such as what metadata fields are returned or whether there are 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?

While extremely short, the description is under-specified rather than appropriately concise. It consists of only two words that add little value, failing to provide minimal useful information 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 that the tool has two parameters with no schema descriptions and no output schema, the description is severely incomplete. It omits what metadata is returned, how parameters affect results, and any additional context needed for correct invocation.

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

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

Schema description coverage is 0%, meaning the parameter names (instance, dataset_id) have no explanations in either schema or description. The description 'Dataset metadata.' does not clarify the role or format of either parameter, failing to compensate for the missing 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 is a single noun phrase 'Dataset metadata.' which restates the tool name without a verb or specific resource. It does not clearly state an action, making it ambiguous whether the tool retrieves, updates, or performs another operation on metadata.

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 usage guidance is provided. There is no indication of when to use this tool versus siblings like 'datasets' or 'records', nor any prerequisites or context for invocation.

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, openWorldHint=true, and destructiveHint=false, so the tool is clearly non-destructive. The description adds no additional behavioral context such as pagination behavior, result limits, or any potential 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 extremely concise at two words, but this brevity sacrifices clarity and usefulness. It does not provide any structured information or context, making it borderline under-specification rather than good conciseness.

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

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

Given the tool has 6 parameters, no output schema, and no narrative about return values or behavior, the description is critically incomplete. It fails to inform the agent about what the search returns, how to construct queries, or any 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?

The input schema contains 6 parameters with only 33% having descriptions. The tool description does not explain any parameter meanings or usage, leaving the agent to rely solely on schema descriptions for 'facet' and 'instance'. This is insufficient for the 4 undocumented 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 'Search datasets' clearly indicates a search action on datasets. It is not a tautology and provides a basic understanding of the tool's purpose. However, it lacks specificity about the search scope or context, and does not differentiate from sibling tools like 'dataset' or 'records'.

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 'dataset' for a single dataset or 'records' for records within a dataset. The description does not mention any prerequisites or context for 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, indicating safe read-only operation. The description adds context about browsing and searching, but no further behavioral details needed 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 front-loaded with the core purpose and includes a list of domains, but it could be slightly more concise. Still, 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?

For a discovery tool with no output schema, the description adequately explains what it returns ('top-N most relevant tools with names + descriptions'). The annotations and schema cover the rest.

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 has 100% description coverage, with clear descriptions for 'query' (natural language examples) and 'limit' (default and max). The description adds no new parameter info but the schema already suffices.

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

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

The description clearly states the tool's purpose: 'Find tools by describing the data or task.' It provides specific examples of domains (SEC filings, financials, etc.) and distinguishes itself from sibling tools by being the first call for exploring available options.

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 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This gives clear when-to-use guidance and implies its role as a discovery tool before other specific 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 declare readOnlyHint=true, openWorldHint=true, destructiveHint=false. The description aligns with these, confirming a read-only, information-gathering operation. It adds valuable behavioral context by listing the types of data returned (filings, fundamentals, patents, news, LEI) and mentions 'pipeworx:// citation URIs', which is not in annotations or schema.

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 with multiple example queries and data type enumeration. It could be trimmed by removing some examples, but it is well-structured and easy to scan. The front-loaded purpose is excellent.

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

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

Given the tool has no output schema and only two simple parameters, the description fully covers what the tool does and what to expect. It mentions return types, citation format, and input constraints. No gaps are apparent.

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 (type and value). The description adds meaning beyond schema: it explains that type only supports 'company' for now, and that value can be ticker or zero-padded CIK but NOT names. It also clarifies the input constraint, which is crucial for correct invocation.

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

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

The description starts with a clear, action-oriented statement: 'Get everything about a company in one call.' It lists specific data types (SEC filings, revenue, patents, news, LEI) and provides example user queries, making the tool's purpose unmistakable. It also distinguishes itself from sibling tools by noting it replaces calling 10+ specialized 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 states when to use (e.g., 'tell me about X', 'brief me on Tesla') and provides precise input requirements: ticker or zero-padded CIK. It also tells users when NOT to use it (if only have a name) and directs them to resolve_entity first. This gives clear decision 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 and openWorldHint=true, but the description adds no additional behavioral context (e.g., whether it returns a list or counts). It does not contradict annotations but provides no value beyond them.

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

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

The description is too terse (three words) at the expense of clarity. Conciseness is not achieved when critical information is missing.

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, low schema coverage, and three ambiguous parameters, the description is grossly insufficient. A user or agent cannot understand what the tool returns or how 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?

With 0% schema description coverage, the description must compensate by explaining parameter meaning. It does not; 'facet', 'instance', and 'dataset_id' remain unexplained. The description adds no 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 'Facet distinct values' is vague and does not specify what a facet is or what the tool does. It fails to distinguish from sibling tools like 'dataset' or 'records'. The purpose is unclear.

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. The description does not mention any context for usage, leaving the agent without decision support.

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, so description's 'delete' aligns but adds no extra behavioral context. Description does not elaborate on reversibility or permissions, which annotations partly 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?

Two concise, front-loaded sentences with zero waste. Every word 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?

For a simple delete tool with one parameter and good annotations, the description is fully sufficient—covers purpose, usage, and pairing with siblings.

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 has 100% description coverage for the single 'key' parameter. Description adds no additional parameter detail beyond what schema provides, earning 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?

Clearly states 'Delete a previously stored memory by key' using specific verb 'delete' and resource 'memory'. Mention of 'remember' and 'recall' distinguishes 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?

Explicitly lists when to use: 'when context is stale, task done, or clear sensitive data'. Also advises pairing with 'remember and recall', providing clear context and 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 indicate readOnlyHint=true and destructiveHint=false, so the behavior is safe. However, the description adds no additional behavioral context, such as whether the parameter is optional or what happens if omitted.

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 ('Instance metadata.') which is under-specified. Conciseness is not an excuse for lacking essential 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 low schema coverage and no output schema, the description should provide substantial context. It fails to explain what metadata is returned, how the parameter is used, or how this tool fits among siblings.

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 one 'instance' parameter with 0% description coverage. The tool description does not explain its purpose, format, or effect. The parameter remains entirely undocumented.

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 states 'Instance metadata' but does not specify what kind of instance (e.g., compute instance, database instance) or what metadata is included. Purpose is vague and fails to clearly differentiate from sibling 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?

No guidance is provided on when to use this tool vs alternatives such as dataset or entity_profile. The description gives no context about the tool's applicability or prerequisites.

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 rate limit (5 per identifier per day), non-destructive nature, and team reading frequency. Adds context beyond annotations (which show non-readonly, non-destructive, non-openworld). 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?

Concise yet comprehensive: 5 sentences covering purpose, usage, behavioral notes, and parameter tips. Front-loaded with the core purpose, no fluff.

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

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

For a simple feedback tool, the description is complete: covers what, when, how, and constraints (rate limits, quota). No output schema needed; the team processes feedback internally.

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 value by advising to describe issues in terms of Pipeworx tools/packs and to be specific, which helps agents craft better messages.

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: submitting feedback (bugs, features, data gaps, praise) to the Pipeworx team. It distinguishes itself from sibling tools (data retrieval, analysis) by being a feedback channel.

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

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

Provides explicit when-to-use scenarios (bug, feature gap, praise) and what to avoid (pasting user prompts). Also mentions rate limits and that it doesn't count against quota, helping agents decide 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 indicate readOnlyHint=true, openWorldHint=true, destructiveHint=false. The description adds beyond that by detailing the tool's behavior: it walks child markets, searches for related markets, groups them, checks monotonicity, and returns ranked opportunities. This provides useful behavioral context 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 moderately lengthy but well-structured, with explicit mode breakdown and examples. It is front-loaded with the main purpose, then modes, then return info. Every sentence adds value, though slight shortening could improve conciseness.

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

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

No output schema is provided, so the description compensates by stating the returns: 'ranked opportunities with suggested trade direction + reasoning'. It covers input, modes, and outputs sufficiently for a tool of this complexity.

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

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

Input schema has 100% coverage with descriptions for both parameters. The description adds meaning by explaining the two modes and providing examples, clarifying that 'event' can be a slug or full URL and 'topic' is a seed question. This goes beyond the schema definitions.

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

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

The description clearly states the tool's purpose: finding arbitrage opportunities on Polymarket by checking monotonicity violations. It distinguishes itself from siblings by explaining two modes (event and topic) and why the cross-event mode is necessary for cases missed by single-event search.

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

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

The description explicitly tells when to use each mode: event mode for a single Polymarket event slug, and topic mode for cross-event comparisons. It provides an example of when topic mode catches cases event mode misses. It does not explicitly state when not to use, but the context is clear enough.

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

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

Annotations (readOnlyHint=true, destructiveHint=false) declare safety, and the description adds behavioral context: scanning, grouping by asset, caching price history, computing model probabilities, and ranking by |edge|. It 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 front-loaded with the main purpose and provides necessary detail in a few sentences. It is efficient without being overly terse, though it could be slightly shorter.

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

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

No output schema exists, but the description explains the return value ('top N ranked by edge magnitude with suggested trade direction'). It covers inputs, process, and output, making it complete for a tool with three optional parameters.

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

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

Input schema covers all three parameters with descriptions (100% coverage). The description adds minimal extra meaning, only reinforcing the 'top N' concept for limit. 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 verb 'scan' and the resource 'highest-volume Polymarket markets', and distinguishes from sibling tools like polymarket_arbitrage by specifying the use case and model ('V1 covers crypto-price bets'). The purpose is 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 identifies the tool as built for the 'what should I bet on today' question, indicating when to use it. It does not explicitly list alternatives or when not to use, but the context is clear enough.

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

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

Annotations already mark the tool as read-only and non-destructive. The description adds the ability to list all keys by omitting the argument and specifies scoping to an identifier, providing 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 concise sentences that front-load the main action, then provide usage context and relationships. No filler or redundancy.

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

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

For a simple read tool with one optional parameter and no output schema, the description adequately covers retrieval, listing, scoping, and pairing. Minor omission: what happens on missing key (likely returns null/empty).

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 schema already describes the single optional parameter. The description merely restates that omitting it lists all keys, adding minimal new meaning beyond what the schema provides.

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

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

The description clearly states the tool retrieves a saved value or lists all keys, with explicit reference to its sibling operations (remember/forget). The verb 'Retrieve' and resource 'saved keys/values' are 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 provides concrete examples (target ticker, address, notes) and explains the tool is for looking up previously stored context. Though it doesn't explicitly state when not to use it, the pairing with remember and forget is implied.

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 readOnly and non-destructive. The description adds behavioral details: it fans out in parallel to multiple sources, returns structured changes with citations, and explains accepted date formats. No contradictions.

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

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

The description is concise, well-structured, and front-loaded with purpose and examples. 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 no output schema, the description adequately explains return format (structured changes, total_changes, URIs). It covers inputs, behavior, and output, providing sufficient context for an AI agent.

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

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

Schema covers all parameters (100% coverage). The description adds practical meaning for the 'since' parameter (ISO date vs. relative shorthand) and suggests typical values, which aids correct usage beyond schema.

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

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

The description clearly states that the tool retrieves recent changes for a company from multiple sources (SEC EDGAR, GDELT, USPTO) in a time window. It is specific and distinct from sibling tools like entity_profile.

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

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

The description provides explicit example queries and contexts for use, such as 'what's happening with X?' or 'brief me on what happened with Microsoft this quarter'. It does not discuss when not to use or alternatives, but the guidance is sufficient.

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

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

Annotations already indicate read-only, non-destructive behavior. Description adds no extra behavioral context (e.g., response format, filtering logic).

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 a mere fragment, not a sentence. Overly terse to the point of being uninformative.

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 9 parameters and no output schema, description fails to explain tool's functionality, return values, or parameter usage entirely.

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

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

Schema has 9 parameters with 0% description coverage. Description provides no explanation of parameters like 'q', 'where', 'select', etc., leaving agent uninformed.

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 'Records in a dataset.' is vague; lacks a verb indicating action (e.g., list, search). Does not differentiate from sibling tools like 'dataset' or 'datasets'.

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. No mention of prerequisites or context.

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

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

Annotations indicate write operation (readOnlyHint=false) and non-destructive. Description adds scope (by identifier), persistence details (authenticated persistent, anonymous 24h), and 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 concise sentences covering purpose, usage, and behavior. Every sentence adds value with no redundancy.

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

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

No output schema, but return value is implicit for a store operation. Covers key aspects: scope, lifetime, and sibling tools. 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 covers both parameters with descriptions. Description adds contextual examples (e.g., 'subject_property') and explains how values are stored, enhancing schema meaning.

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 saves data for reuse across conversations or sessions, with specific verb 'save data' and resource 'key-value pair'. It distinguishes from sibling tools 'recall' and 'forget'.

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

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

Explicitly states when to use ('discover something worth carrying forward') and provides clear alternatives: 'Pair with recall to retrieve later, forget to delete.' No ambiguity.

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

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

Annotations already indicate safe read-only behavior. Description adds that it returns IDs plus pipeworx:// citation URIs and replaces multiple lookup calls, providing useful behavioral context 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?

Extremely concise: four sentences with no wasted words. Front-loaded with action and purpose, examples immediately follow. 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?

Despite no output schema, description covers return format (IDs + citation URIs) and notes efficiency gains. Sufficient for the tool's simplicity and supported by clear 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%, but description adds clarifying examples (e.g., 'For company: ticker, CIK, or name') that go beyond the basic schema descriptions, aiding correct parameter usage.

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

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

The description clearly states it looks up canonical identifiers for companies or drugs, listing specific ID systems (CIK, ticker, RxCUI, LEI) and providing examples. It distinctly separates from sibling tools that require these IDs.

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

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

Explicitly instructs to use this tool before others needing official identifiers. While it doesn't list alternatives, the context is clear and guides sequential usage effectively.

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 openWorldHint. The description adds value by detailing the return structure (verdict modes, structured form, citation) and the data source (SEC EDGAR + XBRL). It also mentions the tool replaces multiple sequential calls, though it doesn't cover error handling or limitations beyond v1 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?

The description is concise: four sentences covering purpose, usage, scope, and return value. It is front-loaded with the core action and avoids redundancy. 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 lack of output schema, the description adequately explains the return value and use case. It notes the limitation to v1 financial claims. However, it does not mention error handling or behavior for unsupported claim types, leaving a minor gap.

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

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

The single parameter 'claim' is fully described in the schema with examples. The description repeats these examples but adds no additional detail about format constraints or validation. With 100% schema coverage, the baseline is 3.

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

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

The description clearly states the tool's purpose: fact-checking, verifying, or validating factual claims against authoritative sources. It uses strong verbs and specifies the resource (company-financial claims via SEC EDGAR + XBRL), distinguishing it from sibling tools like ask_pipeworx or 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?

The description provides explicit usage examples with query patterns (e.g., 'Is it true that…?') and specifies when to use it. However, it does not directly contrast with siblings or state when not to use it, although the context implies it's for factual claims requiring authoritative sources.

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