Tastedive

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

No annotations are provided, so the description carries full burden. It states the tool automatically routes and fills arguments, but lacks details on authentication, rate limits, error handling, or limitations. More transparency on edge cases would be beneficial given the absence of 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 paragraph that is front-loaded with the main purpose and includes helpful examples. It is concise but could be slightly more structured; however, the information density is appropriate.

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

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

For a tool with one parameter and no output schema or annotations, the description covers purpose, usage, and examples. It does not explain return format or error behavior, but given the tool's simplicity, it is fairly 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 schema description coverage at 100% for the single 'question' parameter, the schema already adequately defines it. The description adds example usage but does not provide additional semantic information beyond what is in the schema.

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

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

Description clearly states the tool answers natural-language questions by automatically selecting the appropriate data source. It specifies the verb ('answer') and resource ('natural-language question') and distinguishes itself from siblings by being a general routing tool, whereas siblings like 'compare_entities' or 'entity_profile' are more specific.

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 'Use when a user asks...' and provides concrete examples of query types. It implies the tool is for cases where the agent doesn't want to pick a specific sub-tool, but does not explicitly mention when not to use it or list 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, openWorldHint=true, destructiveHint=false. The description adds that the tool 'fans out to the right packs' and 'returns an evidence packet plus a simple market-vs-model comparison'. This aligns with annotations and provides additional context about internal fan-out logic and output format. No contradiction.

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

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

The description is a single paragraph that front-loads the main action and progressively adds details. It is informative without being overly verbose, though it could be slightly more concise. Every sentence contributes to understanding.

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 covers the output format (evidence packet plus comparison) and explains the processing (fan-out, classification). It provides sufficient context for an agent to understand what the tool does and what it returns. Some minor details like the specific packs for different categories are hinted but not enumerated, which is acceptable.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds value by explaining how 'market' can be a slug, URL, or question text, and implicitly describes 'depth' via 'quick = 2-3 sources, thorough = full fan-out'. While the schema has enum descriptions, the description contextualizes the parameter's effect.

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 researches Polymarket bets by pulling Pipeworx data. It specifies input formats (slug, URL, question text) and output (evidence packet, market-vs-model comparison). This distinguishes it from siblings like ask_pipeworx or compare_entities, which serve different purposes.

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

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

The description provides explicit use cases: 'should I bet on X?', 'what does the data say about this Polymarket market?', 'is there edge in this bet?'. It implies when to use this tool versus others (e.g., for general data queries use ask_pipeworx), but does not explicitly state when not to use it.

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

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

No annotations are provided, so the description carries full transparency burden. It clearly states data sources (SEC EDGAR/XBRL for companies, FAERS/FDA for drugs) and the nature of returned data (paired data + citation URIs). It could mention that the tool is read-only and has no side effects, but the description is honest about its functionality.

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 action and uses five concise sentences. No redundancy; every sentence adds unique information about triggers, entity types, data sources, and efficiency gains. It earns its length.

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

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

Given no output schema, the description adequately summarizes the return format ('paired data + pipeworx:// citation URIs'). It covers both entity types and data categories. Slightly more detail on the return structure (e.g., JSON or table) would improve completeness, but the current description is sufficient for an agent to understand the output.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds value by explaining how each type uses the 'values' parameter (company: tickers/CIKs, drug: names) and what data is pulled for each type, going beyond the schema's basic type hints.

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

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

Description starts with a clear verb and resource: 'Compare 2–5 companies (or drugs) side by side in one call.' It specifies exact types and distinguishes from sibling tools like entity_profile (single entity) and get_recommendations (aggregated suggestions).

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 ('compare X and Y', 'X vs Y', etc.) and intended use cases (tables, rankings). It does not explicitly state when not to use, but the context is clear. Alternatives are not named, but the sibling set implies distinct roles.

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?

No annotations provided, so description carries full burden. Describes behavior: 'Returns the top-N most relevant tools with names + descriptions.' Implies read-only nature with no side effects. Lacks specifics on authentication or rate limits, but adequate for a discovery tool.

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

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

Concise, front-loaded first sentence states purpose, followed by usage context and return description. 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 description explains return format (top-N tools with names+descriptions). Covers input semantics well. Slightly benefits from more response detail, but sufficient for the tool's simple nature.

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% (baseline 3). Description adds meaning to 'query' with examples and to 'limit' with default and max values, exceeding schema details.

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 lists specific domains and distinguishes from siblings by emphasizing discovery and browsing functionality.

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

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

Provides explicit usage context: 'Use when you need to browse, search, look up, or discover what tools exist' and recommends calling it FIRST. Missing explicit when-not-to-use or alternative tool references, but the guidance 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?

With no annotations, the description carries full burden. It discloses the types of data returned and citation URIs. It implies a read-only aggregation but does not mention rate limits, pagination, or performance characteristics. Still, it gives a solid behavioral overview.

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

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

Single paragraph is packed with essential information: purpose, usage triggers, what is returned, and parameter guidance. Every sentence is meaningful and efficiently conveys the tool's value.

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

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

Given the tool's complexity (aggregating from multiple sources), the description covers purpose, usage, return types, and parameters. No output schema exists, but listing the data categories and citation URIs is likely sufficient for an agent. Could mention limits on returned items but overall 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?

Input schema covers 100% of parameters. Description adds value by explaining the enum for type (only company supported), providing examples for value (ticker or CIK), and explicitly stating that names are not supported, which goes 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?

Description clearly states 'Get everything about a company in one call' and enumerates the data categories (SEC filings, fundamentals, patents, news, LEI). It distinguishes itself from sibling tools like resolve_entity and compare_entities by offering an aggregated profile from multiple sources.

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

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

Description provides explicit 'when to use' examples (user asks 'tell me about X' etc.) and contrasts with needing to call 10+ pack tools. It also advises using resolve_entity if only a name is available, providing clear alternative.

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

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

Description implies destructive action (delete) and mentions clearing sensitive data. No annotations provided, so description carries full burden; lacks detail on irreversibility or errors but sufficient for simple tool.

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: purpose first, then usage guidelines, then pairing. No superfluous text, each sentence adds unique value.

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

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

Given simplicity (1 param, no output schema), description fully covers purpose, usage, and relation to siblings. No gaps for agent decision-making.

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

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

Schema coverage is 100% for the single parameter key. Description adds minimal context beyond schema (e.g., 'previously stored'), not significantly enhancing semantic 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?

Clearly states the verb 'Delete' and the resource 'previously stored memory by key'. Differentiates from siblings by pairing with remember and recall.

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

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

Explicitly provides when to use: stale context, task done, or clearing sensitive data. Implicitly excludes use for storing or retrieving by pairing with remember and recall.

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?

With no annotations present, the description carries the full burden for behavioral disclosure. It does not specify that the tool is read-only, mention any side effects, authentication needs, or rate limits. The behavioral implications are vague.

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

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

Two concise sentences with no wasted words. The description is front-loaded with the core purpose.

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

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

The description provides some context about additional data returned with 'info=true' but lacks details about the basic response structure. Given no output schema, more detail on return values would improve 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 coverage is 100%, so the description adds marginal value beyond what the schema already provides. It clarifies the role of 'type' and 'info' but does not significantly enhance understanding.

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

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

The description clearly states the tool's purpose: 'Get similar to X recommendations from TasteDive.' It specifies the verb (Get), resource (recommendations), and source, which effectively distinguishes it from sibling tools like 'entity_profile' 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 explains how 'type' and 'info' parameters affect results but does not provide explicit guidance on when to use this tool versus alternatives. No exclusions or alternative recommendations are mentioned.

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?

With no annotations provided, the description carries the full burden. It discloses key behaviors: rate-limited to 5 per identifier per day, free, doesn't count against tool-call quota, and that feedback affects roadmap.

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 yet comprehensive. It front-loads the purpose, then provides usage conditions and constraints in a well-structured paragraph without unnecessary words.

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

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

Despite no output schema, the description fully covers the tool's functionality, usage, and behavioral constraints. It is complete enough for an agent to correctly select and invoke the tool.

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

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

Schema coverage is 100%, so baseline is 3. The description adds extra context by explaining each enum value for 'type' and providing usage guidance for 'message' (avoid pasting prompts). This enhances parameter understanding beyond the schema.

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

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

The description clearly states the tool's purpose: providing feedback about bugs, missing features, data gaps, or praise. It explicitly distinguishes itself from other tools by focusing on feedback to the Pipeworx team.

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

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

The description provides clear guidance on when to use the tool (bug, feature, data_gap, praise) and what not to do (don't paste user prompt). However, it does not explicitly mention when not to use it, such as for general queries.

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

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

Description adds behavioral context beyond annotations: it is a read-only check (consistent with readOnlyHint=true), describes two modes of operation, and notes the return value (ranked opportunities with trade direction + reasoning). No contradiction with annotations.

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

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

Concise (~150 words), well-structured with 'TWO MODES' highlighted, front-loaded with core purpose. Every sentence adds value, no wasted words.

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

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

Despite no output schema, description states the tool returns 'ranked opportunities with suggested trade direction + reasoning'. Both parameters are fully explained. Covers all important aspects: purpose, modes, and return value.

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. The overall description links each parameter to its mode ('event' for single-event mode, 'topic' for cross-event mode), providing meaning beyond the schema definitions. Clear mapping.

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

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

Description clearly states it finds arbitrage opportunities on Polymarket by checking monotonicity violations. It names two distinct modes (event and topic) and explains what each does, distinguishing the tool from potential siblings like polymarket_edges.

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

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

Description explains when to use each mode: pass an event slug for single-event mode, or a topic/seed question for cross-event mode. It also clarifies why cross-event mode exists (Polymarket may list cutoffs as separate events), but does not explicitly state when not to use this tool or mention alternative 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?

Describes the underlying algorithm (lognormal model from FRED + coinpaprika), data fetching pattern (fetches each asset's price history ONCE), ranking by edge, and output with trade direction. Annotations already indicate read-only and non-destructive; description adds rich detail 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?

First sentence provides the core purpose, followed by technical details and use case. Slightly lengthy but every sentence adds value, no wasted words.

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

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

Given the tool's complexity (scanning, grouping, modeling) and no output schema, the description explains both process and output format. Covers data sources, default parameter values, and intended use case comprehensively.

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 already describes all three parameters with 100% coverage, including defaults and max/min. The description mentions defaults again but adds no new meaning beyond the schema, meeting the baseline for high schema coverage.

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

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

Clearly states scanning Polymarket markets for discrepancies with Pipeworx data, with specific verb 'scan', resource 'highest-volume Polymarket markets', and outcome 'return where disagreement is largest'. Distinguishes from siblings by focusing on opportunity discovery for betting decisions.

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

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

Explicitly frames the tool for the 'what should I bet on today' question, indicating when to use it. Does not explicitly exclude alternatives or mention when not to use, but the context is clear enough for an AI agent.

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 scoping to identifier, retrieval behavior, and listing behavior. No annotations to support, but description adds adequate transparency for a simple read operation.

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 concise sentences, front-loaded with main 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?

No output schema provided, and description does not specify return format (e.g., string, array). Adequate but leaves some uncertainty about response structure.

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

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

Schema coverage is 100% with clear description for 'key' parameter. Description adds no new semantic value beyond restating that omitting key lists all keys. Baseline 3 is appropriate.

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

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

The description clearly states the tool retrieves a value by key or lists all keys when omitted. It distinguishes from siblings by referencing 'remember' and 'forget' for saving and deleting.

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

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

Explicitly says when to use: to recall context stored earlier. Mentions pairing with remember and forget. Lacks explicit when-not-to-use scenarios 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?

With no annotations provided, the description fully discloses the tool's behavior: it fans out to three external sources (SEC EDGAR, GDELT, USPTO) in parallel and returns structured changes, a count, and citation URIs. It does not mention any destructive actions, which is consistent with a read operation. The disclosure is thorough.

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 (5 sentences) and structured with a clear first sentence stating the core function, followed by example queries, technical details, and return format. No word is wasted, and the most important information is 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 there is no output schema, the description adequately explains the return format (structured changes, count, URIs). It also clarifies the external sources used. However, it does not mention any limits (e.g., max results) or pagination, which might be relevant for large time windows. Still, it is mostly 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?

The schema provides 100% coverage of parameter descriptions, but the tool's description adds meaningful context beyond the schema: it explains the since parameter's accepted formats (ISO date vs relative shorthand) with examples, specifies that type is limited to 'company', and clarifies that value can be a ticker or CIK. This adds value for an agent.

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

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

The description clearly states the tool's purpose: retrieving recent changes related to a company. It uses specific verbs ('What's new', 'get updates') and resources ('company', 'changes'), and includes example user queries that distinguish it from sibling tools like entity_profile 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 explicitly lists when to use the tool (e.g., 'what's happening', 'any updates', 'brief me') and provides concrete examples. However, it does not explicitly mention when not to use it or suggest alternative tools for other contexts, so a slight deduction is warranted.

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?

No annotations exist, so the description bears full burden. It discloses memory persistence behaviors (24-hour for anonymous, permanent for authenticated). However, it does not mention overwrite behavior or size limits, which are minor gaps.

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

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

The description is concise with four sentences, each serving a clear purpose: purpose, usage guidance, persistence note, and pairing with other tools. No fluff or redundant information.

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

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

Given no output schema and no annotations, the description covers purpose, usage, parameters, and behavioral traits adequately. It could mention overwrite handling, but overall it provides sufficient context for a simple key-value store.

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

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

Schema coverage is 100%, but the description adds value by providing naming conventions for keys (e.g., 'subject_property') and clarifying that value accepts any text. This supplements 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 clearly states the tool saves data for reuse across conversations or sessions, with concrete examples like ticker, address, and preference. It differentiates from siblings by naming 'recall' and 'forget' explicitly.

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

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

The description explicitly says when to use ('when you discover something worth carrying forward') and pairs with recall and forget as alternatives. It also notes scoping and persistence nuances (authenticated vs anonymous).

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?

No annotations are provided, so the description bears the full burden of disclosure. It explains that the tool returns 'IDs plus pipeworx:// citation URIs' and lists the ID systems. However, it does not mention whether the operation is read-only, any authentication requirements, or rate limits. Given the absence of annotations, the description is adequate but not exhaustive.

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 approximately 100 words, well-structured, and front-loaded with the core purpose. It includes concrete examples and a brief summary of the ID systems. Every sentence adds value without redundancy or unnecessary detail.

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

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

There is no output schema, so the description must cover return values. It does so by specifying that the tool returns IDs plus pipeworx:// citation URIs, and by giving examples of the returned identifiers for different entity types. For a straightforward lookup tool, this provides sufficient context for an AI agent to understand and invoke it correctly.

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

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

Schema coverage is 100%, meaning both parameters have descriptive comments in the input schema. The description adds value by explaining the broader context of how the output is used, but it does not significantly augment the parameter descriptions beyond what the schema already provides. The baseline of 3 is appropriate.

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

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

The description clearly states the tool's purpose: 'Look up the canonical/official identifier for a company or drug.' It specifies the types of identifiers returned (CIK, ticker, RxCUI, LEI) and distinguishes it from siblings by noting it replaces 2–3 lookup calls and should be used before other tools needing official identifiers.

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

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

The description explicitly advises using the tool 'BEFORE calling other tools that need official identifiers.' It provides concrete examples of when to use it (e.g., 'Apple' → AAPL/CIK, 'Ozempic' → RxCUI) and mentions it replaces multiple lookups. It does not explicitly state when not to use it, but the guidance is clear and actionable.

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

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

No annotations are provided, so the description carries full burden. It discloses the returned verdict types (confirmed, refuted, etc.), extracted structured form, actual value with citation, and percent delta. It also states the domain limitation. Missing details about permissions or 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 concise and informative, with a clear first sentence stating purpose. It avoids verbosity while providing necessary details about functionality and output.

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 (single parameter, no output schema), the description covers all essential aspects: input domain, supported claim types, return values, and efficiency benefits. It is complete for effective use.

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

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

Schema coverage is 100% with a well-described 'claim' parameter. The description adds examples and context but does not significantly enhance understanding beyond the schema, meeting the baseline.

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

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

The description clearly identifies the tool's purpose as fact-checking natural-language claims against authoritative sources, specifically for company-financial data via SEC EDGAR. It uses specific verbs like 'validate' and provides examples, distinguishing it 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?

The description explicitly states when to use the tool (e.g., 'Is it true that…?') and notes the domain of company-financial claims. It mentions replacing multiple sequential calls but does not explicitly list alternative tools for non-financial claims, limiting slightly.

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