Treasury Fiscal

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true. The description adds important behavioral context: default model, the requirement of a BYO API key for Anthropic (with cost implication), and the return structure (per-model {score, confidence, signals, raw_response} + combined view). This goes beyond the annotations without contradicting 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 relatively concise and well-structured, starting with the core purpose and then adding details. All sentences serve a purpose. It is not overly verbose, though it could potentially be slightly more concise.

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

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

Given the tool has 4 parameters and no output schema, the description covers the purpose, parameters, return structure, use cases, and cost implications. It could be slightly more complete by explicitly listing all supported models or mentioning edge cases, but overall it is sufficient 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 description coverage is 100%, so baseline is 3. The description adds value beyond the schema: it explains the default model for 'models', when _apiKey is needed, and that 'context' helps disambiguate. It also describes the return format, which is not in the schema.

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

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

The description clearly states the tool probes LLMs for knowledge about a brand/product/topic and returns a visibility score 0-100. It specifies the default model (Workers AI Llama) and the option to use Anthropic with an API key. This distinguishes it from siblings like 'scan_competitor_ai_presence' which may have a similar but distinct 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?

The description explicitly lists use cases: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.' It does not directly mention when not to use or compare to other tools, but the provided context is sufficient for an agent to infer appropriate scenarios. Sibling tools like 'scan_competitor_ai_presence' might be an alternative, but the description doesn't address that.

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

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

The description reveals that Pipeworx selects the appropriate tool and fills arguments automatically, which is a key behavioral trait. It also indicates the return is the answer. Without annotations, this disclosure is valuable. However, it does not specify limitations (e.g., data freshness, latency, or if the question is out of 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 relatively concise, using three sentences to convey purpose, behavior, and usage. The inclusion of examples is helpful. It could be slightly more structured, but the key 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 the simple input schema (one required string parameter) and no output schema, the description provides sufficient context for an agent to understand the tool's purpose and usage. It could mention the scope of data sources or fallback behavior for completeness, but the current description is adequate.

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 baseline is 3. The description adds significant meaning by explaining that the parameter 'question' should be a natural language description of what the user needs, with examples provided. This goes beyond the schema's simple 'Your question or request in natural language'.

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: answering questions in plain English using the best available data source. It distinguishes itself from sibling tools by acting as a unified query interface, contrasting with more specific tools like treasury_customs_revenue or discover_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 provides clear guidance on when to use this tool: whenever you have a natural language question or request. It advises against manually browsing tools or learning schemas. However, it does not explicitly state when not to use it, such as when a sibling tool would 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?

The description details the tool's internal behavior: resolving the market, classifying the bet, fanning out to specific packs (e.g., crypto+fred+gdelt for BTC bets), and returning an evidence packet with model comparison. Annotations already mark it as readOnly and non-destructive, and the description adds valuable behavioral context beyond that.

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 purpose and then provides details. It is informative without being verbose. Slightly long 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?

Given the complexity of the tool (multi-step research, no output schema), the description covers inputs, process, outputs, and use cases. It lacks error handling or response format details, but overall it is sufficiently complete for an agent to understand its capabilities.

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 100% description coverage, so the baseline is 3. The description mentions the market parameter as slug/URL/text but does not add new meaning beyond the schema. The depth parameter is described only in the schema, not in the 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: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It specifies inputs (slug, URL, question text) and outputs (evidence packet, comparison). It distinguishes from sibling tools by focusing specifically on Polymarket bets.

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 use cases: 'Use for "should I bet on X?", "what does the data say about this Polymarket market?", or "is there edge in this bet?".' It implies it is the preferred tool over manually discovering packs, but does not explicitly exclude alternatives or 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?

Without annotations, the description discloses the return format (paired data + resource URIs) and data sources, giving good insight into behavior, though it omits potential limitations like error handling 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?

Three sentences deliver all key information with no redundancy: the action, parameter examples, return details, and efficiency benefit. Every sentence earns its place.

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

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

The description covers the primary return data and usage context adequately for a tool with no output schema, but lacks information on error cases or entity-not-found scenarios, which would enhance 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?

With 100% schema coverage, the baseline is 3, but the description adds value by providing examples and explaining the data returned for each type, going beyond the schema's minimal 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 specifies the action (compare 2-5 entities side by side) and the resource types (company, drug) with detailed data fields, distinguishing it from sibling tools that likely handle single-entity queries.

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

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

The description implies efficiency by stating it replaces 8-15 sequential calls, providing context for when to use it, but does not explicitly exclude alternatives or 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 must convey behavior. It states that it searches and returns results, but does not mention any side effects or limitations (e.g., no filtering beyond query, no state changes). The description is accurate but could be more detailed about the search mechanism.

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

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

The description is three sentences, front-loaded with the action and purpose. It is concise but includes a useful usage hint. One minor improvement could be omitting the example query detail if it's already in the schema.

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

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

Given the simplicity of the tool (search with query and optional limit), the description is nearly complete. It explains the purpose, when to call it, and what it returns. It could mention the default limit and max explicitly, but those are in the schema.

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

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

Schema coverage is 100%, so the schema already documents both parameters. The description does not add extra meaning beyond what the schema provides (e.g., query examples are in schema description). 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 'Search' and the resource 'Pipeworx tool catalog', and specifies that it returns tools with names and descriptions. It distinguishes itself from siblings by being the tool for discovering tools among 500+ 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?

The description explicitly advises 'Call this FIRST' when many tools are available, providing clear context for when to use this tool versus alternatives. It also gives an example of the query format.

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, but the description discloses return type (pipeworx:// citation URIs), covers all data sources, and implies read-only nature. Lacks explicit statement about safety or error behavior, but is otherwise transparent.

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, front-loaded with the main purpose, and each sentence adds value. No filler; includes efficiency claim, return format, and exclusion for sibling tool.

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 specifies what is returned and the input requirements. It also provides alternatives for name resolution and federal contracts, making the tool well-documented for correct 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%, but the description adds meaningful context: explains that 'type' is currently only 'company', and 'value' can be ticker or CIK, and that names are not supported (requiring resolve_entity). This goes beyond schema descriptions.

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

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

The description clearly states it returns a full entity profile across multiple data sources, listing specific packs (SEC, XBRL, patents, news, LEI). It distinguishes from sibling 'usa_recipient_profile' by noting that federal contracts should use that tool directly.

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 (comprehensive profile), when not to use (federal contracts, use alternative instead), and prerequisites (ticker/CIK, not names; use resolve_entity first). Clear exclusion and alternative provided.

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 clearly states that the tool deletes (destructive action), which is transparent. However, it does not mention any additional behavioral traits like irreversibility, authorization requirements, or side effects. For a destructive operation, this is adequate but could be more explicit.

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 5 words, perfectly concise with no wasted information. It is front-loaded and 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?

Given the tool is simple (one required parameter, no output schema, no nested objects), the description is largely complete. It would benefit from noting that deletion is permanent, but the context is sufficient for correct invocation.

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

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

Schema description coverage is 100%, so the schema already documents the parameter. The description 'Memory key to delete' is consistent with the schema description. However, the description adds no additional meaning beyond what the schema provides, earning a baseline 3.

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

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

The description 'Delete a stored memory by key' is a specific verb+resource combination that clearly states what the tool does. It distinguishes this tool from siblings like 'remember' (create) and 'recall' (retrieve) by focusing on deletion.

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

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

The description implies usage when you need to delete a specific memory, but it does not explicitly state when not to use this tool or mention alternatives. Given the sibling 'recall' for retrieval and 'remember' for storage, the context is implied but not stated.

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

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

The description adds behavioral details beyond annotations, such as fetching the page, extracting title/description/key links, and outputting a standard markdown text blob. Annotations already indicate read-only and non-destructive behavior, so the description enhances understanding of the tool's internal process.

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 two sentences defining the action and output, followed by a bulleted list of use cases. It is front-loaded with the core purpose and avoids unnecessary verbiage, earning its place efficiently.

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 (fetch, extract, output), rich annotations, and full schema coverage, the description is complete. It explains the output format and use cases without requiring an output schema. The description covers all necessary information for an AI agent to select and invoke the tool correctly.

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

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

The input schema has 100% coverage with descriptions for both parameters (url and max_links). The description does not add significant new meaning beyond the schema, as it only restates the default and max for max_links. Baseline of 3 is appropriate given full 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 generates a production-ready llms.txt file for any URL, specifying the output format and use cases. It differentiates itself from sibling tools by focusing on a specific file format for AI crawlers, with no sibling directly providing the same 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?

The description explicitly lists three use cases (client indexing, own project drafting, competitor auditing), providing clear context for when to use the tool. It does not specify when not to use it or mention alternative tools, but the explicit use cases are sufficient for most scenarios.

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

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

Discloses the rate limit of 5 messages per identifier per day and the 'Free' status. No annotations provided, but no important behavioral traits are hidden.

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, purpose stated first, no wasted words. Could be structured with bullet points but still effective.

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

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

Covers main points: purpose, acceptable content, rate limit. Lacks mention of response/acknowledgment but adequate for a simple feedback 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% and schema descriptions are detailed. The description adds minimal extra meaning beyond the schema, 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?

Description clearly states the tool sends feedback to the Pipeworx team and enumerates specific use cases (bug reports, feature requests, missing data, praise). It is distinct from sibling tools which are data retrieval or memory related.

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 guidance on when to use (for feedback) and what content to include, plus a rate-limit warning. Does not explicitly exclude non-feedback use cases, 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 declare read-only, idempotent, open-world, non-destructive. The description adds value by disclosing data source (CF analytics-engine), privacy (no PII), return format (pack, tool, count), and caching (5min-1h).

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, front-loaded with main function, then use cases, then technical details. Every sentence earns its place; 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?

Despite no output schema, the description explains return content (top tools, packs, call volume) and data characteristics. Sufficient for a simple read tool with thorough 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?

Only one parameter 'window' with enum and description in schema. The description adds meaning: defaults, purpose of short vs long windows. Schema coverage is 100%, so baseline is 3, but the additional context earns a 5.

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 returns top tools, packs, and call volume over a window, with specific use cases. It differentiates from siblings like 'discover_tools' by focusing on trending data derived from CF analytics.

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: discovering hot data sources, confirming canonical tools, aligning with use cases. Also explains window selection trade-offs (short vs long windows). No exclusions needed.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds behavioral context: the tool checks monotonicity, returns ranked opportunities with trade direction, and explains how cross-event search works. 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 somewhat long but well-structured: purpose first, then mode explanation with examples. Every sentence adds value. Minor redundancy in listing mode details could be tightened.

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 adequately explains return format ('ranked opportunities with suggested trade direction + reasoning'). It covers both modes and their use cases, making the tool's behavior fully understandable.

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), but the description adds significant value beyond parameter names and types. It explains the function of each parameter (event mode vs topic mode) with examples and clarifies the resulting behavior.

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 'Find arbitrage opportunities' on the resource 'Polymarket related markets'. It distinguishes itself from sibling tools by detailing two specific modes (event and topic) and explaining cross-event arbitrage detection, which is unique.

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 outlines two modes and when to use each, with concrete examples. It implies when not to use single-event mode (e.g., when markets are in separate events). However, it lacks explicit 'do not use' or alternative tool names.

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

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

Annotations indicate read-only, open-world, non-destructive. The description adds context beyond annotations: describes the model (lognormal from FRED + live coinpaprika), process (scans top markets, groups by asset, fetches price history once), and output (top N with direction). 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 a single paragraph that front-loads the main purpose and process. It is informative but 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?

Given no output schema, the description explains what is returned (top N ranked by edge with direction) and the underlying logic. It covers the tool's behavior sufficiently for an agent to use 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 description coverage is 100%, so the description does not need to add much. It mentions default values that are also in the schema, adding no extra meaning. Baseline score 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 uses a specific verb ('scan') and resource ('Polymarket markets'), clearly states the goal of finding where Pipeworx data disagrees with market price, and distinguishes this from siblings like 'polymarket_arbitrage' and 'bet_research' by focusing on edge discovery.

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

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

The description explicitly frames the tool for the 'what should I bet on today' question, indicating when to use it (opportunity discovery). It does not mention when not to use it or alternative tools explicitly, but the context of sibling tools implies differentiation.

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, and idempotent behavior. The description adds significant context: explains that the spread is an 'arb signal' due to differing participant pools, describes the return format (leg-by-leg prices, spread in percentage points), and notes the typical price difference range (2-25pp). 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 yet comprehensive, using clear section headers ('TWO MODES') and bullet-like structure. Every sentence adds value, with no redundant explanations. The most critical information (purpose, modes, return values) 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?

Despite lacking an output schema, the description fully explains return values (prices in 0-1, spread as percentage points). It covers all parameters, modes, and the underlying rationale. For a tool with three optional parameters and no nested objects, this is complete.

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

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

Schema coverage is 100%, but the description adds substantial meaning: it lists all topic shortcuts explicitly, explains that explicit tickers/slugs override topic-mapped values, and provides real-world examples. This goes well beyond the schema's minimal 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's function: computing cross-venue spreads between Kalshi and Polymarket for the same event. It distinguishes itself from siblings by specifying the cross-venue focus and listing concrete use cases.

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

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

The description provides clear guidance on when to use the tool through two explicit modes (topic and custom) with examples. However, it does not explicitly state when not to use it or compare directly with siblings like polymarket_arbitrage.

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 clearly states the tool is for retrieval only (non-destructive) and implies persistence across sessions, but does not mention any rate limits or potential side effects. It is accurate and adds value beyond the 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?

Two sentences, no wasted words. Front-loaded with the core action ('Retrieve... or list...'), then adds context. Every sentence earns its place.

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

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

Given a simple tool with one optional parameter and no output schema, the description is complete enough. It explains both modes of use and the purpose. No gaps are evident for the tool's complexity.

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

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

Schema description coverage is 100%, so the schema already documents the parameter well. The description adds context by explaining the behavior when key is omitted (list all), which is a useful semantic beyond the schema's description.

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

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

The description uses specific verbs ('retrieve', 'list') and resources ('memory', 'memories'), clearly distinguishing between single key retrieval and listing all keys. It differentiates itself from sibling tools like 'remember' and 'forget'.

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

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

The description explicitly states when to omit the key ('list all stored memories') and provides context for use ('retrieve context you saved earlier'), but does not explicitly say when not to use it or mention 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?

No annotations are provided, so the description must disclose behavior fully. It describes the parallel fan-out to SEC EDGAR, GDELT, USPTO and mentions return format (structured changes, total_changes count, pipeworx:// URIs). It does not mention auth requirements or side effects, but for a query tool this is sufficient.

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

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

The description is concise, with no redundant sentences. It front-loads the purpose ('What's new about an entity since a given point in time'), then efficiently explains inputs, behavior, and output. 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?

The tool has three parameters, no output schema, and moderate complexity (parallel fan-out). The description covers the core purpose, parameter details, return format, and use cases. It is complete enough for an AI agent to understand how and when to 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 has 100% coverage with descriptions for all three parameters. The description adds value by explaining that 'type' only supports 'company', giving examples for 'since' formats, and clarifying that 'value' accepts ticker or zero-padded CIK. This goes beyond the schema basics.

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 function: retrieving what's new about an entity since a point in time. It specifies entity type 'company' and lists three data sources (SEC EDGAR, GDELT, USPTO), making the purpose 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 explicitly suggests use cases: 'brief me on what happened with X' or change-monitoring workflows. It provides examples for the 'since' parameter (ISO date, relative like '7d', '30d', '3m', '1y'). However, it does not explicitly state when not to use or mention alternatives, though context from sibling tools implies entity_profile for static info.

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

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

The description discloses that memory persistence depends on authentication status (authenticated vs. anonymous 24-hour session). This is useful beyond the basic 'store' action. However, it doesn't mention any side effects or limits on key-value size or count.

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 that efficiently cover purpose, use cases, and behavioral nuance. No wasted words; front-loaded with action and resource.

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 only two simple parameters, the description is sufficient. It explains the tool's role in the session memory workflow and its persistence behavior. Minor missing detail: no mention of overwrite behavior for duplicate keys.

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 schema already documents both parameters with examples. The description adds no further parameter-specific details beyond the schema, so the baseline 3 applies.

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

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

The description clearly states the tool stores a key-value pair in session memory, which is specific and actionable. It distinguishes itself from siblings like recall and forget by explicitly describing the save operation.

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 use cases ('save intermediate findings, user preferences, or context across tool calls') and explains persistence differences between authenticated users and anonymous sessions. However, it does not explicitly say when not to use it or mention 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?

No annotations provided, so description carries full burden. It discloses read-only intent (resolve, returns data), versioning, and does not mention side effects or destructive behavior. Lacks details on error handling or limits, but sufficient for a lookup 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?

Two sentences: first defines purpose and key benefit, second details version, inputs, and outputs. No filler, every sentence contributes meaning. Front-loaded with the most important 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 simple schema (2 params, no nesting, no output schema) and no annotations, the description covers essential functionality, input forms, and output items. Minor omission: no mention of error cases or performance, but overall adequate.

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

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

Schema already provides 100% coverage with param descriptions; description adds significant value by explaining the input format variants (ticker, CIK, name) with concrete examples and version context for the type parameter.

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 resolves an entity to canonical IDs, specifying version, type, input formats (ticker, CIK, name), and output components (ticker, CIK, company name, resource URIs). Distinct from sibling tools which are general query, memory, or treasury-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?

Describes efficient single-call resolution, replacing 2-3 lookups, with explicit examples of valid values (AAPL, 0000320193, Apple). Does not explicitly exclude cases or name alternatives, but context implies it's the optimized choice for entity lookup.

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 mark it as read-only, idempotent, and non-destructive. The description adds key details: probes each entity via ai_visibility_check, returns ranked list with score/confidence/signal density, and treats first entity as a narrative subject—all beyond annotation 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?

Three sentences effectively convey purpose, method, use case, and output. It is front-loaded and avoids fluff, though the middle sentence could be slightly tighter. Still, very 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?

Given the tool's moderate complexity (multi-entity comparison) and the complete schema descriptions, the description explains the output format (ranked list with metrics) and the underlying mechanism (using ai_visibility_check). 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?

Schema covers all 4 parameters with descriptions, so baseline is 3. The description adds value by explaining the 'entities' parameter's special role (first entry is subject) and reiterating that 'models' and '_apiKey' are optional. This extra context justifies a 4.

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

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

The description explicitly states it compares AI visibility across multiple entities side-by-side, using ai_visibility_check to probe each, ranking by score, and identifying most/least recognized. This clearly distinguishes it from the sibling tool 'ai_visibility_check' (single entity check) and other competitors.

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 a clear use case example ('does Claude know about us as well as our competitors?') and implies usage for competitive audits. It does not explicitly state when not to use it, but the sibling tool 'ai_visibility_check' suggests single-entity cases are handled separately.

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 the burden. It indicates a read operation ('Get') but lacks details about data freshness, pagination, or potential delays. Annotations could have provided more safety info.

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

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

The description is two sentences, each adding value. No fluff, front-loaded with the main 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?

Given no output schema and a simple tool, the description is adequate but could mention the data range or return format for 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% (only 'limit' parameter). The description adds context by noting 'default 12 for 1 year,' which clarifies the default behavior 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 uses a specific verb ('Get') and resource ('monthly US customs duty revenue collections from the Treasury'), clearly distinguishing it from siblings like treasury_debt or treasury_receipts by specifying the exact revenue type.

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 says 'Useful for tracking tariff revenue impact over time,' which implies a usage context but does not explicitly state when not to use it or compare with 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?

The description mentions it returns historical data points, but does not elaborate on other behaviors like rate limits, data freshness, or pagination. Since annotations are empty, the description carries the full burden, but it provides some useful context beyond the 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 concise (two sentences) and front-loaded with the core purpose. 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 tool has a simple schema and no output schema, the description adequately explains what it does. It could mention the format of historical data (e.g., date, amount), but is still sufficient for an agent to select and invoke correctly.

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

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

Schema description coverage is 100%, so the schema already documents the 'limit' parameter. The description does not add extra meaning beyond 'returns historical data points', which is not directly about the parameter.

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 returns the current US national debt with historical data points. The verb 'Get' and resource 'US national debt' are specific. It distinguishes from sibling tools like treasury_customs_revenue, treasury_exchange_rates, and treasury_receipts by targeting debt data.

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

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

The description implicitly indicates this is for retrieving debt data, and the context of sibling tools suggests alternatives for other treasury data. However, there is no explicit 'when to use' or 'when not to use' guidance.

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

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

Annotations are empty, so the description must carry the burden. It describes the data source (US government official rates) but does not disclose any behavioral traits like update frequency, data freshness, or whether rates are historical or current. No contradictions.

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

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

Two sentences, zero waste. Front-loaded with the action and resource, followed by a clarifying statement. Every sentence serves a 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?

Given the simple input schema and no output schema, the description is mostly complete. It explains the data source and scope. Missing details like default limit behavior or response format could be added, but the tool is straightforward.

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 value by explaining that rates are 'official' and used by the US government, but it does not add detail about the parameters beyond what the schema already 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 verb (Get), resource (Treasury exchange rates), and scope (for a specific country). It distinguishes itself from sibling tools like treasury_customs_revenue and treasury_debt by specifying currency conversion rates, which are unique to this tool.

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 context on what the tool does but does not explicitly say when to use it vs. alternatives. No exclusions or comparisons to siblings are given, leaving the agent to infer based on the resource name.

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

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

Annotations are empty, so description must disclose behavior. It states that data is broken down by source, which is helpful, but lacks details on pagination, date range, or response format. 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?

Single sentence, perfectly sized, front-loaded with key action and resource, no waste.

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

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

For a simple tool with one param and no output schema, the description is mostly adequate. However, it lacks context on output format or data source recency, which could be useful 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%, and the only parameter 'limit' is described in the schema. The description adds no extra param info, but with full coverage, a score of 4 is justified as the schema does the heavy lifting.

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 ('Get') and clearly states the resource ('total US government receipts') and the breakdown by source categories (individual income tax, corporate tax, etc.), which effectively distinguishes it from siblings like treasury_customs_revenue.

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 explicit guidance on when to use this tool versus siblings, such as treasury_debt or treasury_customs_revenue. The description implies usage for receipts data but does not provide context 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?

No annotations are provided, so the description carries full burden. It discloses the return structure (verdict, extracted form, actual value with citation, percent delta) and the scope (v1 supports only company-financial claims), providing clear behavioral expectations.

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 very concise (two sentences) while covering purpose, scope, and output. It is front-loaded with the action and resource, making it easy to parse.

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 (fact-checking), the single parameter, and lack of output schema or annotations, the description is remarkably complete. It explains input type, supported domain, return structure, and even provides example claims.

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 100% coverage with a description for the only parameter 'claim'. The description adds example claims but does not provide additional semantic meaning beyond what the schema already states.

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 fact-checks natural-language claims against authoritative sources, specifically company-financial claims for public US companies. It lists the possible verdicts and replaces multiple sequential agent calls, distinguishing it from siblings.

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

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

The description explicitly says it supports company-financial claims via SEC EDGAR + XBRL, implying it should be used for such claims. It mentions it replaces 4-6 sequential agent calls, providing context but not explicitly stating when not to use it or listing alternatives.

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