Dataverse Harvard

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: routes to 1,423+ tools across 392+ sources, returns structured answer with 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?

Concise yet informative, front-loaded with the key directive. Examples are slightly extensive but remain relevant. No wasted sentences.

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

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

For a simple tool with one parameter and no output schema, the description covers the overall function, mechanism, and output type. Adequate for an agent to understand its role.

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. The description adds usage examples but does not provide additional semantic detail beyond what the schema says ('natural language question'). Meets 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 routes factual questions to authoritative structured data sources with citations, explicitly contrasting with web search. It lists many example use cases, making the purpose unmistakable.

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

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

Provides clear directive to prefer over web search for factual questions and gives numerous examples. Lacks explicit when-not-to-use scenarios but the contrast with web search implies the boundary.

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, safe behavior. The description adds internal logic: market resolution, bet classification, and pack fan-out. It does not mention error handling or rate limits, but overall it gives a clear behavioral model that 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 concise at 5 sentences, front-loads the core action, explains input flexibility, internal logic, and use cases. Every sentence adds necessary information without redundancy.

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

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

Given the tool's complexity, the description covers input, classification, fan-out, and output. It lacks details on the output format (e.g., structure of evidence packet), but since no output schema is provided, this is acceptable. The use cases and differentiation from siblings are well-covered.

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

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

The schema covers both parameters with descriptions. The description adds value by explaining the depth enum ('quick = 2-3 sources, thorough = full fan-out, default thorough') and the flexibility of market input (slug, URL, or question text).

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: to research a Polymarket bet by fetching Pipeworx data. It distinguishes itself from sibling tools by positioning itself as the core demo product that saves agents from having to discover packs manually.

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

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

The description explicitly provides three use cases ('should I bet on X?', 'what does the data say?', 'is there edge?') and hints that it is more convenient than manual pack discovery. However, it does not directly contrast with specific sibling tools like ask_pipeworx or compare_entities.

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 show readOnlyHint=true, destructiveHint=false. Description adds that it pulls data from specific sources (SEC EDGAR/XBRL for companies, FAERS and FDA for drugs) and returns citation URIs. Does not contradict annotations.

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

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

Description is well-structured with clear sections and front-loaded purpose. Slightly verbose but every sentence serves a purpose; no wasted words.

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

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

Given there are only 2 parameters with enums and no output schema, the description comprehensively covers input expectations, data sources, output format (paired data + citations), and use cases.

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, but the description adds value by explaining how to fill values (tickers/CIKs for company, drug names for drug) and how type affects data. Examples further clarify.

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

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

The description explicitly states the tool compares 2-5 companies or drugs side by side, with specific verbs ('compare', 'stack up') and resources. It distinguishes itself from sequential calls by noting it replaces 8-15 agent 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?

Clearly states when to use it (user says 'compare X and Y', 'X vs Y', wants tables/rankings) and provides examples. Implicitly differentiates from alternatives like making multiple entity_profile or search calls.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false. Description adds no new behavioral traits beyond stating it returns 'metadata'.

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 sentence, no extraneous words, front-loaded with purpose. Highly efficient.

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

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

For a simple one-parameter tool with annotations and no output schema, the description provides the essential purpose and parameter format, sufficiently 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?

With 0% schema description coverage, the description adds meaning by specifying the format as a DOI persistent ID with an example, compensating for the lack of schema descriptions.

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

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

The description clearly states the tool retrieves dataset metadata by DOI persistent ID, with a specific example. This distinguishes it from siblings like dataset_files and 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?

It implies usage when a DOI is available and provides a format example. Does not explicitly state when not to use or mention alternatives, but context with siblings makes it clear.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, indicating a safe read operation. The description adds no further behavioral context (e.g., pagination, result format, or constraints). Does not contradict annotations, but adds minimal 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?

Very concise single sentence with no wasted words. However, the brevity sacrifices important detail such as parameter purpose and output expectations. Still, it is efficient for what it includes.

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 one parameter, no output schema, and simple operation, the description is minimally complete for a listing tool. However, without any output description or parameter context, the agent lacks sufficient information to use the tool correctly. Below average.

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 required parameter 'persistent_id' has 0% schema description coverage, and the description provides no additional meaning (e.g., it does not explain that this is a dataset identifier or how to find it). This is a critical gap for tool 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?

Description clearly states the action: listing files in a dataset. The verb 'list' and resource 'files' are specific. However, it does not mention that the dataset is identified by a persistent ID, which could cause confusion with sibling tools like 'dataset' that operate on datasets directly. Slightly above average.

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. Sibling tools include 'dataset' (likely manages dataset metadata) and 'dataverse' (manages dataverses), but no explicit comparison or exclusions are provided. Below average.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, making the tool's safety profile clear. The description adds that it retrieves metadata by alias or id, which is consistent but not particularly insightful 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 a single sentence with no unnecessary words, making it efficient and front-loaded.

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

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

Given the tool's simplicity (1 parameter, no output schema) and strong annotations, the description is minimally adequate. However, it lacks details on what metadata is returned or how to formulate identifiers, which reduces completeness.

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 'identifier' has no description in the schema (0% coverage). The description says 'by alias or id' but does not clarify format or examples, leaving the agent to infer acceptable 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?

The description states the tool retrieves 'Dataverse (collection) metadata by alias or id', which indicates the action and resource but is vague about what exactly constitutes 'metadata'. It differentiates from siblings only by naming the resource, but lacks specificity.

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

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

No usage guidelines are provided. The description does not indicate when to use this tool versus siblings like 'dataset' or 'entity_profile', nor does it mention 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?

Annotations indicate read-only behavior which matches description. Description adds value by explaining it returns top-N relevant tools with names and descriptions, going beyond annotations to clarify 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?

Three sentences with no redundancy. Purpose is front-loaded, domains are listed, and usage guidance is included. Every sentence is necessary and efficient.

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

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

For a simple tool discovery function with full schema coverage and good annotations, the description provides complete context: purpose, when to use, input parameters, and output format. 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?

Both parameters have descriptions in the input schema (100% coverage). Description does not add significant meaning beyond schema; it mentions 'top-N' which aligns with limit parameter but does not elaborate beyond schema defaults.

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 'Find tools by describing the data or task' with a specific verb and resource. It distinguishes from sibling tools by positioning itself as a discovery tool to be called first, contrasting with specific tools like 'search' or 'validate_claim'.

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

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

Explicitly lists when to use: for browsing, searching, or discovering tools in specified domains. Also advises to call it first to see options, implying alternative of using a known tool directly. Lacks explicit when-not-to 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. Description adds transparency by detailing return contents (filings, fundamentals, patents, news, LEI) and mentions citation URIs. Does not contradict annotations, but could mention potential rate limits or latency.

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 four sentences, front-loaded with clear purpose, and every sentence adds meaningful information. No redundancy or 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?

Given complexity (aggregating multiple APIs) and lack of output schema, description lists all major return categories (filings, fundamentals, patents, news, LEI). Sufficient for agent to understand what to expect, though could mention data freshness or limits.

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

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

Schema coverage is 100% (both parameters described). Description adds value by clarifying that type only supports 'company' and value can be ticker or CIK, plus explicit note that names require resolve_entity first — information not in schema.

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

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

Description states 'Get everything about a company in one call' and lists specific data sources (SEC filings, fundamentals, USPTO patents, news, LEI). It clearly differentiates from sibling tools by implying aggregation of multiple sources, 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 specifies when to use: 'when a user asks tell me about X' etc. Also provides when-not: 'Names not supported — use resolve_entity first if you only have a name.' This gives clear guidance on prerequisites 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 already indicate destructive behavior (destructiveHint=true). The description reinforces this by stating 'Delete', and adds context about clearing sensitive data. No contradictions, but adds minimal new behavioral info 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 two concise sentences with no wasted words. Every sentence serves a purpose: defining the action and providing usage context.

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

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

For a simple one-parameter destructive tool with clear annotations, the description is complete. It covers the purpose, usage, pairing with siblings, and data sensitivity considerations. No need to explain return values as per guidelines.

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% parameter description coverage (the key parameter is described as 'Memory key to delete'). The tool description does not add additional parameter semantics beyond what the schema provides, so baseline 3 is appropriate.

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

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

The description clearly states the action 'Delete a previously stored memory by key' using a specific verb and resource, and distinguishes itself from siblings like 'remember' and 'recall' by mentioning pairing.

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

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

Explicitly states when to use the tool: 'when context is stale, the task is done, or you want to clear sensitive data.' Also provides pairing guidance with 'remember' and 'recall', effectively communicating alternatives.

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

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

Discloses that feedback is read daily, directly affects roadmap, is rate-limited to 5/day/identifier, and is free with no tool-call quota impact, consistent with annotations (destructiveHint=false).

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?

Four well-organized sentences with front-loaded action verb, no fluff, 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 three parameters (two required, one nested), the description covers purpose, use cases, behavioral notes, and parameter guidance completely without needing an output schema.

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

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

Adds context beyond schema: explains enum values for type, advises on message content, and clarifies context is optional, despite 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?

Clearly states the tool collects feedback (bug, feature, data_gap, praise) and distinguishes from sibling tools like ask_pipeworx and discover_tools by its specific purpose.

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 describes when to use for each feedback type, advises against pasting end-user prompts, mentions rate limits and quota-free usage, and implicitly directs other queries to siblings.

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

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

Annotations (readOnlyHint=true, destructiveHint=false, openWorldHint=true) are consistent. Description adds rich behavioral context: walking child markets, searching across events, grouping, checking monotonicity, and returning ranked opportunities with suggested trade direction and reasoning.

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 approximately 100 words, well-structured with clear sections, front-loaded with purpose. 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?

Despite no output schema, description explains return of ranked opportunities with suggested direction and reasoning. Both modes are fully explained with no gaps. The tool's complexity is adequately covered.

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. Description adds significant meaning: explains event mode takes slug or URL, topic mode takes a seed question and searches across events, and clarifies the difference and 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 explicitly states the tool finds arbitrage opportunities on Polymarket by checking monotonicity violations. It clearly distinguishes two modes (event and topic) and differentiates from sibling tools like polymarket_edges by explaining cross-event mode catches cases single-event mode misses.

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 each mode: event for a single event slug, topic for cross-event related markets. Includes an example scenario where cross-event mode is necessary, helping the agent decide correctly.

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 behavior. The description adds details about grouping by asset, fetching price history once, computing model probability, and ranking by edge, which aligns with and enriches the annotation hints.

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

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

The description is somewhat long but well-organized, front-loading the core purpose and using clear sentences. It could be slightly tighter, but 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 lacking an output schema, the description explains the return format (top N ranked by edge with suggested direction) and the underlying process (model, data sources). This is adequate for a read-only discovery tool.

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

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

Schema coverage is 100%, so baseline is 3. The description adds context like 'ranks by edge' and 'suggested trade direction', which clarifies how parameters affect output beyond the 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 uses specific verbs ('scan', 'return') and resources ('highest-volume Polymarket markets', 'Pipeworx data'), clearly distinguishing the tool's function from siblings like polymarket_arbitrage and bet_research. It explains the model and algorithm concisely.

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

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

The description explicitly states the use case: 'Built for the what should I bet on today question' and explains how it avoids manual paging. It implies when to use but does not explicitly mention when not to use or compare to siblings.

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

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

Annotations already provide readOnlyHint=true and destructiveHint=false. The description adds scoping and pairing context, which is valuable but not critical beyond annotations.

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

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

Two sentences, highly efficient, front-loaded with purpose. No redundant words.

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

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

For a simple retrieval tool with one optional param and no output schema, description adequately covers purpose, usage, scoping, and pairing. 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 a single optional key parameter. Description adds that omitting key lists all keys, which is not in the schema, and clarifies key is a memory key, adding 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?

Clearly states it retrieves a saved value or lists all keys, with specific verb 'retrieve' and resource 'value saved via remember'. Distinguishes from sibling tools by mentioning '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 ('to look up context stored earlier'), provides context for not re-deriving, and mentions pairing with remember/forget. Scoping to identifier is also helpful.

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 behavioral details beyond annotations: it fans out to three parallel data sources, accepts both ISO dates and relative shorthand, and returns structured changes with 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?

The description is compact yet comprehensive, using bullet-like lists within sentences. Every sentence adds value: purpose, usage examples, fan-out details, parameter formats, and return structure. 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?

The tool has no output schema, so the description must cover return values, which it does ('Returns structured changes + total_changes count + pipeworx:// citation URIs'). However, it omits potential error conditions (e.g., what if one source fails) or performance considerations for parallel fan-out. Still, it is largely complete for typical usage.

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

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

Schema coverage is 100%, so baseline is 3. The description enhances parameter understanding by explaining that `since` accepts ISO dates or relative shorthand ('7d', '30d', '3m', '1y') and that `value` accepts tickers or zero-padded CIK. This adds practical guidance beyond the schema's descriptions.

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

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

Description opens with a question that clearly states the tool's purpose: 'What's new with a company in the last N days/months?' It lists specific example queries from users and contrasts with sibling tools by stating it fans out to multiple sources (SEC, GDELT, USPTO).

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 multiple example user queries and explicitly says 'Use when a user asks...' which gives clear context. It does not, however, mention when not to use or suggest alternative sibling tools, leaving a minor gap.

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

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

Description adds valuable persistence details (24-hour retention for anonymous, permanent for authenticated) beyond the annotations, which only indicate write and not destructive.

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?

Four well-structured sentences, front-loaded with purpose, no redundant information. Every sentence contributes meaningfully.

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 storage tool, the description covers purpose, usage, persistence, and pairing. Could optionally mention return behavior but overall sufficient.

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. Description adds concrete examples for keys and values, enhancing understanding beyond schema.

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

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

The description clearly states the tool saves data for reuse across conversations/sessions, with specific examples. It distinguishes from siblings (recall, forget) by mentioning pairing.

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

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

Explicit use cases are given (resolved ticker, target address, etc.) and the description advises pairing with recall/forget, providing clear guidance on when to use 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 already cover readOnlyHint, destructiveHint, openWorldHint. Description adds that it returns IDs plus citation URIs and replaces multiple lookup calls, going 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 a single paragraph that efficiently conveys key information. Could be slightly more concise but 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 adequately explains return values (IDs plus URIs). For a simple lookup tool with strong annotations and schema, it is complete enough.

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 both parameters with descriptions (100% coverage). Description adds examples but doesn't significantly enhance meaning beyond schema.

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

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

Clearly states it looks up canonical identifiers for companies or drugs, with specific ID systems (CIK, ticker, RxCUI, LEI). Examples make purpose unambiguous and distinguish 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?

Explicitly instructs to use before other tools needing identifiers. Provides examples of when to use, though lacks explicit when-not-to-use advice.

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, covering safety. The description adds no behavioral details beyond the search scope. Since annotations provide the safety profile, the description does not contradict them but fails to add context like pagination or result limits.

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 sentence with no wasted words. It is concise but could benefit from front-loading the scope across multiple types.

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 minimal for a tool with 5 parameters and no output schema. It does not explain return format, pagination, or how to use the optional parameters effectively. Annotations cover safety but not completeness.

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 60%. The description clarifies the 'type' parameter by listing the types, but adds no new meaning for 'query', 'start', or 'sort'. With moderate 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 states the verb 'Search' and lists the resources (datasets, files, dataverses), making the purpose clear. However, it does not distinguish itself from sibling tools like 'dataset' or 'dataset_files', which might have overlapping 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?

No guidance on when to use this tool versus alternative tools (e.g., 'dataset' for a specific dataset). The description lacks explicit usage recommendations or context about when not to use it.

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

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

Description fully discloses behavior beyond annotations: it details the data source (SEC EDGAR + XBRL), return values (verdict, extracted form, actual value with citation, percent delta), and the fact that it replaces multiple calls. Annotations already indicate read-only and non-destructive, so description adds rich 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 well-structured and concise, covering all key aspects in a few sentences. It is front-loaded with the core purpose and usage, then details return and supported domain. Slightly longer than minimal but earned its length with useful 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 thoroughly explains return values (verdict types, structured form, citation, percent delta) and the source. It contextualizes the tool as a replacement for multiple steps, ensuring an agent understands its capabilities and limitations fully.

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

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

The single parameter 'claim' is fully described in the schema with 100% coverage. The description adds example claims and clarifies the expected natural-language format, providing additional semantic meaning beyond the schema's basic description.

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

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

The description clearly states the tool's purpose: fact-checking natural-language factual claims against authoritative sources, specifically company-financial claims for US public companies. It distinguishes itself from sibling tools by noting it replaces multiple sequential calls, making its unique value clear.

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

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

Explicitly states when to use: 'when an agent needs to check whether something a user said is true' and provides example queries. It specifies the supported domain (company-financial claims via SEC EDGAR + XBRL) and the return type, offering clear guidance on appropriate usage.

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