Openfoodfacts

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description adds value by explaining that the tool routes the question among 1,423+ tools, fills arguments, and returns structured answers with stable pipeworx:// citation URIs. No contradictions with annotations.

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

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

The description is efficiently structured: starts with a strong preference directive, lists domains, explains internal routing, provides usage cues, and ends with examples. Every sentence contributes, no filler.

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 (routing among 1,423+ tools), the description covers purpose, usage boundaries, internal behavior, and output format (structured answers with citations) without needing an output schema. It is comprehensive for an agent to decide and use correctly.

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

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

Schema coverage is 100% with a single 'question' parameter described as 'Your question or request in natural language'. The description reinforces this with examples of acceptable queries, adding moderate value beyond the schema. 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's purpose: to answer factual questions using authoritative structured data with citations. It explicitly opposes web search for sourcing queries about SEC filings, FDA drug data, and many other domains, with concrete examples like 'current US unemployment rate'.

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 when-to-use guidance: 'PREFER OVER WEB SEARCH' for specific data types and question formats ('what is', 'look up', 'find', etc.). It lists many domains and example queries, making it clear when to invoke this tool over 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 clearly indicates the tool is read-only (fetches data), does not destroy anything, and its open-world nature. It explains the depth parameter behavior ('quick = 2-3 evidence sources, thorough = full fan-out'). This adds meaningful context beyond the annotations (readOnlyHint, openWorldHint, destructiveHint).

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 well-structured, front-loading the main action. It uses 4-5 sentences efficiently, with no wasted words. Each 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's complexity and lack of output schema, the description adequately explains inputs, the process (resolve, classify, fan-out), and the output (evidence packet + comparison). It could be more specific about the output format, but it provides enough context for an agent to understand what to expect.

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 already describes both parameters with 100% coverage: market (slug, URL, or question text) and depth (enum with quick/thorough). The description repeats this information but does not add substantial new semantics beyond stating that depth affects the number of evidence sources. 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's purpose: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It details the process (resolves market, classifies bet, fans out to packs) and output (evidence packet plus market-vs-model comparison). Example use cases are provided, making the purpose unmistakable.

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

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

The description explicitly lists when to use the tool: 'Use for "should I bet on X?", "what does the data say about this Polymarket market?", or "is there edge in this bet?"' It positions the tool as the core demo product. However, it does not explicitly mention when not to use it or differentiate from sibling tools like 'polymarket_arbitrage' or 'polymarket_edges'.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds no additional behavioral context, such as pagination behavior, result limits, or data freshness.

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

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

The description is extremely concise (two words), but it sacrifices informative value. While brevity is good, a few more words to clarify parameters would improve it without losing conciseness.

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

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

Given the tool has 3 parameters, no output schema, and no parameter descriptions, the description is insufficient. It lacks details about pagination, expected output format, and how to use the parameters effectively.

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

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

Schema description coverage is 0% and the description does not explain any parameters. 'brand' is implied but 'page' and 'page_size' are completely undocumented, leaving the agent without guidance on required formats or defaults.

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

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

The description 'Products by brand.' clearly states the tool's function: retrieving products filtered by brand. This distinguishes it from sibling tools like 'category' or 'product' which likely have different filtering scopes.

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

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

No guidance is provided on when to use this tool versus alternatives like 'category' or 'search'. It does not specify prerequisites, exclusions, or context for use.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is clear. However, the description adds no extra behavioral context (e.g., pagination behavior, result limits) beyond what annotations cover.

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

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

The description is extremely concise (4 words) but lacks substance. It is not a tautology, but every word could be more informative. The brevity is not earned by covering key details.

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

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

Given the complexity (3 parameters, no output schema, many siblings), the description fails to explain pagination, return format, or use cases. It is insufficient for an agent to confidently 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 0%, so description must compensate. It hints that 'category' filters products but does not explain 'page' or 'page_size' (likely pagination). Only one of three parameters gains meaning from 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 'Products by category.' indicates the resource (products) and filter (category), but lacks a clear verb (e.g., 'List', 'Get'). It does not differentiate from sibling tool 'product', which may be confusing.

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

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

No guidance on when to use this tool versus alternatives. The description only implies usage when filtering products by category, with no exclusions or pointers to related tools.

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

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

Annotations declare readOnlyHint=true, destructiveHint=false, and description adds that data comes from SEC EDGAR/XBRL, FAERS, FDA approvals, and trials. It states returns 'paired data + pipeworx:// citation URIs' and performance benefit. No contradictions and rich behavioral context beyond annotations.

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

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

The description is a compact paragraph front-loaded with main purpose, then trigger examples, then type-specific details, then a performance note. Every sentence earns its place; 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?

With no output schema, the description covers return format (paired data + citation URIs), data sources, and performance. It fully equips an agent to understand what the tool does and what to expect, making it complete for its 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 coverage is 100% with descriptions for 'type' and 'values'. Description goes further: explains what each type fetches (financials vs drug data), gives examples (AAPL, ozempic), and mentions data sources. This adds significant meaning beyond the schema.

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

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

The description clearly states 'Compare 2–5 companies (or drugs) side by side in one call.' This is a specific verb+resource+scope, and it distinguishes this tool from siblings like entity_profile or search, which handle single entities or general 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 explicitly lists trigger phrases ('compare X and Y', 'X vs Y', 'how do X, Y, Z stack up', 'which is bigger') and use cases like tables/rankings. It also notes that it replaces 8–15 sequential calls, implying alternatives. This gives clear guidance on when to invoke.

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

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

Annotations already indicate read-only and non-destructive behavior. The description adds no further behavioral details (e.g., pagination, result limits, or edge cases), contributing little beyond the annotations.

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

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

The single sentence is too brief to convey necessary information; it sacrifices clarity for brevity. The description is under-specified rather than efficiently 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?

With no output schema, three undocumented parameters, and a skeletal description, the tool's complete context is missing. An agent cannot reliably use this tool without guessing required formats or behavior.

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

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

Schema description coverage is 0%, yet the description does not explain parameters. The country parameter is only implicit, and page/page_size are entirely undocumented. The description fails to add meaning beyond the raw 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 'Products from a country.' implies retrieval of products but lacks an explicit action verb like 'list' or 'get'. It distinguishes minimally from siblings (e.g., 'product' tool) but does not clearly state the tool's function.

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

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

No guidance on when to use this tool versus alternatives like 'brand' or 'category'. The description does not specify prerequisites or context for invocation.

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

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds that it returns 'the top-N most relevant tools with names + descriptions,' which is useful but does not significantly extend behavioral knowledge beyond what annotations imply. 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 front-loaded with the core purpose and guidance. However, it includes a long list of example domains that, while helpful, could be trimmed without losing clarity. Overall, it is reasonably concise for the information conveyed.

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 simple functionality (discovery), schema covers parameters, and the description explains what is returned (top-N names+descriptions). No output schema exists, but the description sufficiently covers the return value. Minor omission: no mention of ordering or relevance criteria, but acceptable for a discovery tool.

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

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

Schema description coverage is 100% (both 'query' and 'limit' have descriptions). The description does not add new parameter details but provides example query strings that illustrate usage. Since the schema already documents parameters adequately, 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's purpose: 'Find tools by describing the data or task.' It provides a specific verb (find) and resource (tools), and it distinguishes itself from sibling tools by being a discovery/search tool. The list of example domains further clarifies what kind of tools can be discovered.

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 when to use this tool: 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' It also gives contexts like 'browse, search, look up, or discover what tools exist.' This provides clear guidance against alternatives.

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

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

Annotations already indicate read-only and non-destructive behavior. The description adds value by detailing the returned data (filings, fundamentals, patents, news, LEI) and the citation format, giving agents a clear behavioral picture beyond annotations.

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

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

The description is a single, well-organized paragraph. It front-loads the purpose, gives usage cues, lists outputs, and explains input constraints. Every sentence earns its place without redundancy.

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

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

Despite no output schema, the description covers return data types and constraints. It mentions 'recent' and 'latest' for timeliness. Could be improved by noting any limits (e.g., pagination), but overall sufficiently complete for a profile 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 parameters are documented. The description adds usage hints: type only supports 'company' with future expansion, and value should be ticker/CIK not name, with a redirect to resolve_entity. This adds meaningful context.

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

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

The description clearly states the tool's function: 'Get everything about a company in one call.' It provides specific example queries and distinguishes the tool from needing multiple other tools, making its purpose very clear.

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

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

Explicitly states when to use (user asks for info about a company, or to avoid calling many tools) and when not (names not supported; suggests using resolve_entity first). This provides excellent usage guidance.

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

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

Annotations already set destructiveHint=true, so description is consistent but adds context about clearing sensitive data. 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 efficient sentences, no fluff, front-loaded with the main action.

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

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

Given the tool's simplicity (1 param, no output schema) and high-quality annotations, the description covers all necessary context: when and why to use it, and related tools.

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

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

Input schema has 100% description coverage for the single parameter 'key'. Description does not add extra semantic value beyond what the schema provides.

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

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

The description clearly states the verb 'Delete' and the resource 'memory by key'. It distinguishes from sibling tools like 'remember' and 'recall' by being the deletion counterpart.

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: stale context, task completion, or clearing sensitive data. Also advises 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?

The description discloses rate limiting ('Rate-limited to 5 per identifier per day') and cost ('Free; doesn't count against your tool-call quota'). These add significant behavioral context beyond annotations (readOnlyHint=false, etc.). No contradictions with annotations.

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

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

The description is compact and front-loaded: it opens with the action, then conditions, then tips. Every sentence serves a purpose (usage guidance, behavioral notes, formatting rules). 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 simplicity (feedback submission, no complex output), the description covers all needed aspects: when to use, how to formulate feedback, constraints (rate limit, quota-free), and team handling. No output schema needed, but the description implies the feedback is recorded and acted upon.

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 coverage is 100% with detailed descriptions. The description further clarifies the `type` enum values and provides usage examples (e.g., 'Describe the issue in terms of Pipeworx tools/packs'). While the schema does the heavy lifting, the description adds slight contextual value.

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

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

The description clearly states the tool's purpose: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It enumerates specific feedback types (bug, feature/data_gap, praise) and distinguishes from sibling tools like ask_pipeworx and search by focusing on reporting issues to the 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 explicit guidance: 'Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise).' It also instructs on how to frame feedback and mentions rate limits, offering clear context for invocation.

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

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

Annotations already indicate the tool is read-only and nondestructive. The description adds behavioral context by explaining the logic (monotonicity checks) and return value (ranked opportunities with reasoning). 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 detailed but well-structured, with the main purpose first, followed by mode breakdowns and examples. It is slightly lengthy but efficient, earning its place without redundancy.

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

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

Given no output schema, the description sufficiently explains return values (ranked opportunities with trade direction and reasoning). It covers the tool's complexity (two modes, cross-event search) and the rationale behind them, making it complete for a read-only analytical 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 value by elaborating on each parameter's role in the respective mode (e.g., event slug for single-event mode, topic for cross-event mode), going beyond the schema descriptions.

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

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

The description clearly states the tool's purpose: finding arbitrage opportunities on Polymarket via monotonicity violations. It distinguishes two modes (event and topic) and explains their use cases, making it easy for an agent to select the correct mode.

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 guidance on when to use each mode, with an example of cross-event mode catching scenarios missed by event mode. It does not explicitly state when not to use the tool, but the modes cover the primary use cases adequately.

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

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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description adds rich behavioral details: V1 coverage, model source, grouping by asset, one-time price history fetch, probability computation, and ranking by |edge|. No contradictions with annotations.

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

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

The description is a single paragraph that front-loads the purpose and provides necessary technical details. It could be slightly trimmed but is largely efficient and well-structured.

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 explains return values ('top N ranked by edge magnitude with suggested trade direction') but lacks details on the output structure (e.g., fields per edge). Given no output schema, this is adequate but not fully complete.

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

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

Schema coverage is 100% with clear descriptions. The description adds context for parameters (e.g., 'top N edges', 'volume window', 'minimum |edge| in percentage points'), but does not significantly exceed schema details. 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's purpose: scanning high-volume Polymarket markets to find where Pipeworx data disagrees with market price and returning the top edges. It specifies the model (crypto-price bets, lognormal from FRED + coinpaprika) and the output (ranked edges with suggested trade direction). This distinguishes it from siblings like polymarket_arbitrage.

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

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

The description explicitly targets the 'what should I bet on today' use case and mentions discovery without manual paging. It does not explicitly state when not to use or list alternatives, but the context is clear and sufficient for an agent to decide.

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 annotations declare readOnlyHint=true and destructiveHint=false, so the agent knows it is a safe read operation. The description adds no behavioral context beyond the purpose, and does not disclose any traits like rate limits or data freshness.

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

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

The description is extremely concise at four words, but this comes at the cost of completeness. While not wasteful, it is under-specified for effective tool use.

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

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

Given the lack of output schema and the simple input, the description fails to specify what the tool returns, how to interpret the output, or any edge cases. The annotations help with safety but do not provide functional completeness.

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

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

The input schema has one parameter 'barcode' with 0% description coverage. The description does not explain the expected format, valid values, or any constraints of the barcode, leaving the agent with no additional meaning beyond the parameter name.

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 'Product by barcode.' clearly indicates the tool looks up product information using a barcode. However, it is vague about what specific product data is returned, and does not differentiate from sibling tools like 'brand' or 'category'.

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

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

No usage guidelines are provided. The description does not indicate when to use this tool versus alternatives such as 'search' or 'brand', nor does it mention any prerequisites or context.

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

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

Annotations already provide readOnlyHint=true. The description adds valuable behavioral context: scoped to an identifier, and the ability to list all keys. No contradictions.

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

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

Three sentences, each adding unique value. Efficiently covers purpose, usage, and pairing. 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?

Given the simple parameter and clear annotations, the description adequately explains behavior and use cases. Lack of output schema is not critical here.

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 the single parameter with full description. The description adds extra semantics: 'omit the key argument' to list all keys, enhancing understanding beyond schema.

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

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

The description clearly states the verb 'Retrieve' and the resource 'a value previously saved via remember' or list all keys. It distinguishes from siblings by explicitly mentioning 'remember' and 'forget' as paired 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 explains when to use the tool (look up stored context like user's target ticker, address) and how to use it (omit key to list all). It also provides scoping and pairing 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?

The description adds significant context beyond annotations: it fans out to SEC, GDELT, USPTO; describes output shape (structured changes, count, URIs); and explains 'since' parameter format. Annotations already confirm read-only and non-destructive.

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

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

The description is a single dense paragraph but contains all key information. It is front-loaded with the purpose. Could be more structured with bullet points, but still 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 complexity (multiple sources, date formats), the description covers the essentials. Lacks mention of error handling or performance, but for a read-only tool with openWorldHint, it's adequate. Output schema is absent, but description partially compensates.

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 description adds practical guidance: explains 'since' formats (ISO date vs relative shorthand with examples), and clarifies 'value' as ticker or CIK. This enhances 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 it retrieves recent changes for a company, with specific example queries. It distinguishes from siblings like 'entity_profile' and 'search' by focusing on temporal updates across 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?

Explicitly lists when to use with example user questions. Does not explicitly state when not to use, but the context is clear. Could mention alternatives like 'search' for broader 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?

Annotations provide basic hints (readOnly=false, destructive=false), but description adds important details: storage as key-value scoped by identifier, persistence differences (authenticated vs anonymous), and 24-hour retention. No contradiction.

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

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

Concise, front-loaded purpose, each 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?

Covers purpose, usage scope, behavioral traits, and pairing with siblings. No output schema needed as return is implied (success indicator likely trivial). Complete for a store-retrieve 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 already describes both parameters with 100% coverage. Description adds naming convention examples for key (e.g., 'subject_property') and clarifies value can be any text, going slightly 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 the tool saves data for later reuse, with specific use-case examples (resolved ticker, target address) and names sibling tools (recall, forget) for differentiation.

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

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

Explicitly tells when to use ('when you discover something worth carrying forward') and implicitly when not to, plus explicitly pairs with recall (retrieve) and forget (delete).

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: returns IDs plus pipeworx:// citation URIs, examples of output formats. Annotations already indicate read-only and non-destructive, so description complements well.

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

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

Four sentences, front-loaded with core purpose, examples, and sequencing advice. No redundant or vague language.

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 covers return values (IDs + citation URIs) and usage context. Adequate for the tool's complexity (two entity types, multiple ID systems).

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 detailed descriptions for both parameters. Description reinforces with examples and usage context, but does not add new parameter info beyond schema. A score of 4 reflects effective reinforcement.

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

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

The description states a specific action: look up canonical/official identifiers for entities. It clearly distinguishes from sibling tools by focusing on identifiers needed by other tools, not general entity profiles or searches.

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

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

Explicitly states when to use: when a user mentions a name and needs identifiers like CIK, ticker, RxCUI, LEI. Also advises to use before other tools that need official identifiers. Lacks explicit when-not-to-use, 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?

The description adds no behavioral context beyond what annotations already provide (readOnlyHint, openWorldHint, destructiveHint). It does not mention pagination, sorting, or any effects of open world hint, missing an opportunity to enrich agent understanding.

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

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

The description is extremely concise (two words), but conciseness sacrifices clarity. It front-loads nothing useful and lacks structure. Every sentence should earn its place; here, it does not.

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 (5 parameters, no output schema, many siblings), the description is incomplete. It omits return format, pagination behavior, and how to effectively use parameters like sort_by or fields. An agent would need to guess or look elsewhere.

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 40%, only 2 of 5 parameters have descriptions in the schema. The description does not elaborate on parameters like page, page_size, or query semantics, failing to compensate for the low 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 'Full-text search' states the verb and resource but is too generic. It does not specify what is being searched (e.g., products, entities) and fails to distinguish from sibling tools like product, category, or brand, which also involve searching.

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

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

No guidance is provided on when to use this tool versus alternatives like product or category search. There is no mention of context, prerequisites, or 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?

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false. The description adds value by detailing the return structure (verdict types, extracted form, actual value with citation, percent delta) and noting that it replaces multiple calls. However, it does not disclose potential limitations like rate limits or coverage boundaries beyond the v1 domain.

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 action and scope, then lists output details and efficiency gains. Every sentence serves a purpose without redundancy, though it could be slightly more concise by removing the list of verdict types (since those are return values).

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 one simple input and no output schema, the description adequately explains the return values and domain limitation. It covers purpose, usage, and output, making it sufficient for an agent to decide when to invoke it and what to expect. Missing explicit error handling or call to mind.

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% for the single parameter 'claim', so the baseline is 3. The description provides examples but does not add additional semantic meaning beyond what the schema already provides (e.g., format constraints or elaboration on what constitutes a valid claim).

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 ('Fact-check, verify, validate, confirm/refute') and clearly identifies the resource ('natural-language factual claim against authoritative sources'). It distinguishes this tool from potential multi-step alternatives by stating it replaces 4-6 sequential calls.

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

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

The description explicitly states when to use the tool ('when an agent needs to check whether something a user said is true') and provides example queries. It does not explicitly list when not to use it or name alternative tools, but the domain restriction ('v1 supports company-financial claims') implicitly guides appropriate use.

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