Opencitations

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

The description discloses key behavioral traits: it automatically routes to the correct tool, fills arguments, returns structured answers with citation URIs. It is consistent with annotations (readOnly, openWorld, non-destructive) and adds context beyond what annotations provide, such as the citation format and the breadth of sources.

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 lengthy with multiple examples and a full paragraph of use cases. While it is front-loaded with the preference statement, it could be more concise without losing clarity. About 2-3 sentences would suffice; the current version is somewhat verbose.

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 parameter) and rich annotations, the description adequately covers what the tool does and how it behaves. It mentions output format (structured answer with citations) despite no output schema. However, it could briefly note that it does not perform actions or mutate data, but annotations already cover that.

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 one parameter 'question' described as 'natural language'. The description reinforces that the question is in natural language and provides examples, but adds little additional semantic meaning beyond the schema since the schema already conveys the required information.

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 by routing to specialized tools across trusted sources. It uses a specific verb ('routes'), identifies the resource (structured data with citations), and distinguishes itself from sibling tools like 'web search' and 'citation' tools.

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

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

The description explicitly says 'PREFER OVER WEB SEARCH' and provides detailed usage guidelines including specific domains (SEC filings, FDA drug data, etc.) and query patterns ('what is', 'look up', 'find'). It also gives concrete examples, leaving no ambiguity about when to use this tool.

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

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

Annotations already declare readOnlyHint and openWorldHint. Description adds beyond: classifies bet, fans out packs, returns evidence and comparison. 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?

Four sentences, all earning their place. Front-loaded with purpose and usage. Slightly lengthy but no wasted words.

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

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

No output schema, but description explains returns: evidence packet plus comparison. Covers core functionality well for a complex 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%, baseline 3. Description adds meaning: explains depth quick vs thorough, and market can be slug, URL, or question text, enhancing semantic clarity.

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 researches Polymarket bets by pulling Pipeworx data, using specific verb+resource. It distinguishes from siblings by focusing on bet edge and implied probability.

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

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

Provides explicit use cases ("should I bet on X?", "is there edge?") and explains the fan-out process. Lacks explicit when-not-to-use or alternatives, but context is clear.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description does not add any behavioral details beyond that, which is acceptable given the annotations. No contradiction is present.

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 concise sentence, front-loaded with the core action. It is appropriately sized for a simple tool, though it could be slightly expanded 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 no output schema and a single parameter, the description lacks information about what the tool returns (e.g., a JSON object, success/error codes). This is insufficient for an agent to fully understand the tool's 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?

The description explains that 'oci' stands for Open Citation Identifier, adding meaning beyond the schema's bare 'string' type. However, it does not provide format or validation rules, which would be helpful given 0% schema description 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 it retrieves a single citation using an Open Citation Identifier (OCI), which differentiates it from sibling tools like 'citations' (likely multiple). However, it does not define what a citation is or specify the return format, leaving some ambiguity.

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 no guidance on when to use this tool versus alternatives (e.g., 'citations' for multiple results, 'references' for different IDs). No context about prerequisites or when not to use is given.

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 already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description adds that it returns a count rather than a list, which is useful but minimal. More details on error handling or response format would improve transparency.

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 (one short sentence). However, conciseness should not come at the expense of completeness; here it is adequate but borderline under-specified.

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 sibling tools like 'references_count' and 'citations', the description does not clarify the difference in output (count vs. list). No output schema is provided, leaving the agent uncertain about the return format.

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 simply restates that the parameter is a DOI ('for a DOI'). It adds no additional meaning beyond the schema, failing to compensate for the lack of parameter 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 provides an 'incoming-citation count' for a DOI, using a specific verb and resource. However, it does not differentiate itself from sibling tools like 'citations' or 'references_count', which could lead to confusion.

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. Given sibling tools with similar names (e.g., 'citations', 'references_count'), the agent lacks criteria for choosing this one.

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

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

Annotations already indicate readOnlyHint=true and openWorldHint=true. The description 'DOIs that cite the given DOI' adds no additional behavioral context (e.g., pagination, result format, or that it returns a list). It fails to disclose traits beyond what annotations provide.

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 (four words) and front-loaded. It conveys the core purpose without extraneous words, though it could be slightly expanded for clarity.

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 (one parameter, no output schema), the description is incomplete. It does not state that the result is a list of DOIs, mention any limitations (e.g., direct citations only), or address the openWorldHint implications. Important context for an agent is missing.

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 description effectively explains the 'doi' parameter: it is the DOI for which citing DOIs are returned. Since schema description coverage is 0%, the description fills the gap by clarifying the parameter's role, even though it does not add format or validation details.

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

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

The description 'DOIs that cite the given DOI' clearly indicates the tool returns citing DOIs for a given DOI. It contrasts with siblings like 'citation' (singular) and 'references' (likely opposite direction). However, it lacks an explicit verb like 'retrieve' or 'list'.

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 related siblings like 'citation', 'citation_count', or 'references'. The description does not mention alternatives 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 declare readOnlyHint and destructiveHint false; description adds data sources (SEC EDGAR/XBRL, FAERS, FDA, trials) and return format (paired data + citation URIs), enriching beyond annotations.

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

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

Description is somewhat lengthy but well-organized with clear purpose first. Every sentence adds value, though minor redundancy in listing examples 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?

Despite no output schema, description explains return data (paired data, citation URIs) and covers usage context, data sources, and triggers comprehensively for a multi-entity comparison 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 description adds context for each parameter: explains what each 'type' ('company' or 'drug') entails and what 'values' should contain (tickers vs drug names), plus data pulled per type.

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 compares 2–5 companies or drugs side by side, with specific verb 'compare' and resource 'entities'. It distinguishes from siblings like entity_profile by focusing on multi-entity comparison.

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

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

Explicitly lists user phrases that trigger this tool (e.g., 'compare X and Y', 'X vs Y', etc.) and mentions it replaces 8–15 sequential calls, but does not explicitly state when not to use it.

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

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

Annotations indicate read-only, non-destructive. Description adds that it returns top-N most relevant tools with names and descriptions, providing 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?

Two sentences, front-loaded with action. The second sentence is long but information-dense; could be slightly trimmed but remains clear.

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 specifies return format (tool names+descriptions, top-N). Parameter coverage is complete. Sufficient 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?

Both parameters have full schema description. Description adds natural language query examples and clarifies the limit defaults/maximum, significantly augmenting schema.

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

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

Description states 'Find tools by describing the data or task' with a clear verb and resource. It distinguishes from sibling tools which are specific domain tools, making this a meta-discovery 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?

Explicitly advises 'Call this FIRST when you have many tools available and want to see the option set'. Does not mention alternatives but provides strong contextual guidance.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds valuable behavioral details: returns specific data (SEC filings, fundamentals, patents, news, LEI) with pipeworx:// citation URIs. 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?

The description is somewhat long but well-structured: first sentence as purpose, second as usage triggers, third listing return data, fourth on parameters. Every sentence adds value, though slight trimming possible.

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, so description must explain return values, which it does thoroughly. Covers all data types and citation format. Parameters fully described. Complexity of aggregating multiple sources is addressed. Complete for the AI to understand the tool.

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

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

Schema coverage is 100%, but the description adds significant meaning: type only supports 'company', value can be ticker or CIK with examples, and clarifies that names require resolve_entity first. This goes beyond the schema's enum and 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 'Get everything about a company in one call' and provides specific use cases like 'tell me about X', which directly defines purpose. It distinguishes from siblings by mentioning it avoids calling 10+ pack tools across various 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 tells when to use (user queries like 'tell me about X') and when not (names not supported, use resolve_entity). Provides clear context and alternative, making it easy for the AI 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?

Annotations already set destructiveHint=true and readOnlyHint=false; description confirms 'delete' and adds 'clear sensitive data'. No contradiction, but no new behavioral depth beyond annotations.

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

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

Two concise sentences: first states purpose, second gives usage guidance. Front-loaded and no unnecessary words.

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

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

For a simple one-parameter tool with good annotations, description covers purpose, usage timing, and links to related tools completely.

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

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

Schema covers 100% of parameter description with 'Memory key to delete'. Description adds no further detail, meeting baseline for high schema coverage.

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

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

Clearly states it deletes a memory by key (verb+resource). Distinguishes from siblings like 'remember' and 'recall', and mentions pairing.

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

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

Explicitly states when to use (stale context, task done, clear sensitive data). Lacks explicit when-not, but the positive conditions are clear.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, establishing it as a safe read operation. The description adds context about the output being 'bibliographic metadata,' but does not disclose any additional behavioral traits (e.g., rate limits, pagination, or data freshness). Since annotations cover safety, this is minimally adequate.

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-formed sentence that is front-loaded with the essential purpose. There is no superfluous content; every word earns its place. This is ideal conciseness for a simple 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?

Given the low complexity (1 parameter, no output schema, strong annotations), the description is mostly complete. It specifies the input constraints and general output type. However, it could mention the format or common fields of the returned metadata to fully inform the agent, though this is not critical.

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%: the 'dois' parameter is clearly described with type array and min/max count implied. The overall description adds 'comma-separated' but the schema uses array, causing slight inconsistency. Nevertheless, the schema already handles semantics well, and the description adds little extra meaning.

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

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

The description clearly states it returns bibliographic metadata for DOIs, specifying 'one or more' and a limit of 50. The verb 'provide' is implied, and the resource is identified. However, it does not explicitly differentiate from sibling tools like 'citation' or 'references', which may have similar purposes but different outputs.

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 includes a usage hint (comma-separated, ≤50 DOIs), which helps with invocation. However, it does not provide guidance on when to use this tool versus alternatives such as 'citation' for formatted citations or 'references' for reference lists. No when-not or alternative suggestions are given.

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 minimal (false for all hints), but the description discloses rate limits ('Rate-limited to 5 per identifier per day'), cost ('Free; doesn't count against your tool-call quota'), and impact ('signal directly affects roadmap'). 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?

The description is compact yet comprehensive, front-loaded with purpose, then usage, then specifics, then constraints. Every sentence earns its place—no filler, clear hierarchical organization.

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 feedback function, the description covers all essential aspects: purpose, when to use, content guidelines, rate limits, and impact. No output schema is needed for a submit action; the description is self-sufficient.

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

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

Schema coverage is 100% with clear descriptions for each parameter (type, context, message). The description adds value by explaining how to frame feedback in terms of tools/packs and reinforces the type enum contexts. While schema handles the basics, the description enriches understanding.

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

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

The description explicitly states the tool's purpose: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It gives concrete examples (bug, feature, data_gap, praise) and clearly distinguishes from siblings by focusing on feedback versus query, citation, or entity 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 precise when-to-use 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 includes a clear when-not-to: 'don't paste the end-user's prompt.'

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

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

Annotations already indicate readOnlyHint, openWorldHint, and non-destructive behavior. The description adds valuable behavioral details: walking child markets, extracting dates/thresholds, sorting, and reporting violations. It does not contradict annotations.

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

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

The description is a single paragraph that efficiently conveys the concept, logic, and output. It is front-loaded with the core purpose. Slightly verbose but 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?

For a tool with one parameter and no output schema, the description covers the functionality, input format, and output structure. It does not address error handling or edge cases, but the provided context is sufficient for typical 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?

The single parameter 'event' has a schema description that covers slug or URL. The tool description re-emphasizes this with examples, but does not add substantial new information beyond the schema. With 100% schema coverage, baseline is 3.

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

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

The description explicitly states the tool's purpose: to find arbitrage opportunities in Polymarket events via monotonicity violations. It explains the underlying logic with examples, clearly distinguishing it from sibling tools like 'bet_research' or 'polymarket_edges'.

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

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

The description clearly indicates when to use the tool: for events with multiple 'by date' or 'by threshold' markets. It implies the context but does not explicitly state when not to use or provide alternatives. Still, usage intent is well communicated.

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

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

Annotations already indicate readOnlyHint and openWorldHint. The description adds significant behavioral detail: algorithm steps (scans top markets, groups by asset, fetches price history once, computes model probability, ranks by edge), data sources (FRED, coinpaprika), and output. 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?

Every sentence earns its place: purpose, V1 specifics, data sources, algorithm steps, and use case. Front-loaded with core action. No fluff.

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

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

For a moderate-complexity tool with no output schema, the description thoroughly covers what the tool does, how it works (including model and data sources), and what it returns (top N with trade direction). Annotations provide safety context. Complete for practical use.

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

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

Schema coverage is 100%, with each parameter described. The description adds context beyond schema by explaining how parameters are used (e.g., min_edge_pp as a filter, limit for ranking). Baseline is 3 for high coverage; the 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 clearly states the tool scans high-volume Polymarket markets and returns those where Pipeworx data disagrees most with market price. It specifies the verb (scan/return), resource (Polymarket markets), and criteria (edge magnitude), distinguishing 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 states the use case: 'what should I bet on today' — discovering opportunities without manual browsing. It does not explicitly mention when not to use or contrast with alternatives, but the context is clear and sufficient for typical agent 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 indicate readOnlyHint=true. Description adds scoping to user identifier and outlines pairing with remember/forget, which goes 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?

Three sentences, front-loaded with action, each sentence adds distinct value without redundancy.

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

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

Covers retrieval, listing, scoping, and sibling hints. Lacks output format details but is sufficiently complete for a simple 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 fully covers the single 'key' parameter. Description adds that omitting key lists all saved keys, providing essential context beyond schema.

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

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

Clearly states the tool retrieves a saved value or lists keys, with specific verb 'retrieve' and 'list'. Distinguishes from sibling tools remember and forget.

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

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

Explicitly says use to look up context stored earlier, mentions scoping and pairing with remember/forget. Lacks explicit 'when not to use' but provides sufficient 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 indicate readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description adds valuable behavioral context: parallel fan-out to multiple external sources, accepted date formats (ISO and relative shorthand), and the return structure (structured changes, count, citation URIs). This goes beyond the annotations.

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

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

The description is efficient and well-structured. It starts with the core purpose, transitions to usage examples, then details data sources, parameter formats, and return data. Every sentence adds value without redundancy or 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 has 3 parameters and no output schema, the description covers all necessary context: parameter formats and examples, return structure (structured changes, count, URIs), and the parallel data source lookup. It fully prepares the agent to use 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?

Schema coverage is 100%, but the description adds extra semantics: for 'since' it explains both ISO and relative formats with examples and recommends '30d' or '1m' for monitoring; for 'value' it gives ticker and CIK examples; for 'type' it notes that only 'company' is supported today. This builds on 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 opens with a clear question ('What's new with a company...') and lists concrete example queries, establishing the tool's purpose. It explicitly names the three data sources it fans out to (SEC EDGAR, GDELT, USPTO), distinguishing it from sibling tools like entity_profile or compare_entities.

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

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

The description provides explicit usage guidance: 'Use when a user asks...' followed by multiple example queries covering typical scenarios. It also explains the parallel fan-out to three sources, giving the agent context on what to expect. Though it doesn't explicitly state when not to use, the examples are sufficiently comprehensive.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds that it returns DOIs cited by the input, which is consistent. No additional behavioral traits (e.g., pagination, scope, rate limits) are mentioned, but the annotations alleviate some burden.

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, very terse. It is front-loaded but lacks detail that would improve usability. For a tool with one parameter, it is minimally adequate, but not concise in the sense of being information-dense.

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 parameter and no output schema, the description should at least clarify what a DOI is and how it differs from sibling tools. It does not, leaving gaps in understanding, especially with related tools like 'citations' and 'citation_count'.

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

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

Schema description coverage is 0%, meaning the schema provides no parameter descriptions. The description only names the parameter implicitly ('given DOI') but adds no format, constraints, or examples. This leaves the agent to infer that 'doi' is a string identifier, which may be ambiguous.

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 DOIs cited by the given DOI, which is a specific verb+resource. It implies this is the bibliography of the DOI vs. citing references, distinguishing it from sibling 'citations' which likely return DOIs that cite the given DOI.

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 siblings like 'citation', 'citations', 'references_count', etc. The agent must infer the purpose from the name and brief description.

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 profile is clear. The description adds 'outgoing-reference count' but no further details (e.g., behavior on missing DOI, output format). Minimal value beyond annotations.

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

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

Extremely concise with no wasted words. However, it omits important information like output format, making it slightly under-specified despite the tool's simplicity.

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?

Lacks when-to-use guidance vs siblings, no output format description despite missing output schema, and no edge-case behavior. Even for a simple tool, the description leaves gaps.

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

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

The description clarifies that the single 'doi' parameter refers to the source DOI for outgoing references. With 0% schema coverage, this context is helpful but minimal; the parameter name already suggests a DOI string.

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 counts outgoing references for a DOI, a specific verb+resource+identifier. It distinguishes from siblings like 'citation_count' which counts incoming citations. Purpose is unambiguous.

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

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

No guidance on when to use this tool versus siblings like 'citation_count' or 'references'. The agent must infer from naming alone, which is insufficient given the crowded sibling set.

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

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

Annotations indicate readOnlyHint=false (write) and destructiveHint=false. The description adds key behavioral details: key-value storage scoped by identifier, persistence differences between authenticated (permanent) and anonymous (24 hours) users.

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 well-structured sentences. First sentence states the core purpose, second explains when and what to save, third details storage behavior. No filler; every sentence earn 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 the simple two-parameter tool and no output schema, the description fully covers purpose, usage, parameter details, behavioral nuances, and cross-references sibling tools. Nothing more is needed.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds valuable context: examples of keys and values (e.g., 'subject_property', 'target_ticker'), enhancing the schema's meaning.

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

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

The description clearly states the tool's purpose: 'Save data the agent will need to reuse later' — a specific verb and resource. It distinguishes itself from siblings like recall (retrieve) and forget (delete) by explicitly mentioning them.

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 you discover something worth carrying forward'. Provides concrete examples of what to save (ticker, address, preference, subject). Also directs to pair with recall and forget for complementary actions.

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 already declare readOnlyHint=true and destructiveHint=false, so the description adds value by confirming the tool is a lookup and mentioning specific return values (IDs and pipeworx:// citation URIs). However, it doesn't elaborate on edge cases or behavior beyond what annotations imply.

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 (under 100 words) and well-structured: a clear purpose statement, list of ID systems, concrete examples, and usage guidance. Every sentence adds value without redundancy.

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

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

Given no output schema, the description adequately explains what the tool returns (IDs and citation URIs) and includes usage examples. It also mentions that it replaces 2-3 lookup calls, providing context on efficiency. Slightly more detail on the exact output format would improve completeness.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaning by providing examples of valid inputs for each type (e.g., ticker, CIK, or name for company; brand or generic name for drug), which clarifies the schema descriptions. It also references the enum type explicitly.

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 look up canonical/official identifiers for companies or drugs (CIK, ticker, RxCUI, LEI). It provides concrete examples (e.g., 'Apple' → AAPL/CIK) and distinguishes it from sibling tools by emphasizing it is a prerequisite for other tools requiring IDs.

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

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

The description explicitly tells when to use the tool: 'Use this BEFORE calling other tools that need official identifiers.' While it doesn't list specific alternative tools, the context is clear and the instruction is actionable. It could benefit from exclusion cases (e.g., when an identifier is already known), but the guidance is strong.

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 behavioral context: it returns a verdict, structured form, actual value with citation, and percent delta. It also mentions that it replaces multiple sequential calls, indicating internal complexity. No contradictions with annotations, and the description enriches understanding beyond the annotations.

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

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

The description is concise with no wasted words. It is structured logically: first paragraph explains purpose and usage examples, second paragraph details scope, constraints, output, and efficiency. Every sentence adds necessary 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 that there is no output schema, the description adequately covers the return values (verdict, structured form, actual value with citation, percent delta). It also specifies the current domain (company-financial) and data sources (SEC EDGAR + XBRL). Annotations provide safety information. While more details on error handling could be added, the description is sufficiently complete for an agent to use 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?

Input schema has 100% description coverage, so the baseline is 3. The description adds value by specifying that the claim should be in natural language and gives examples (e.g., 'Apple's FY2024 revenue was $400 billion'). This clarifies the expected format beyond the schema description, justifying a score of 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 clearly states the verb (fact-check, verify, validate) and the resource (natural-language factual claim against authoritative sources). It distinguishes itself from sibling tools like citation or entity_profile by specifying its unique fact-checking function, with concrete examples of usage.

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

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

The description explicitly says when to use it ('check whether something a user said is true') and provides query examples. It also notes the current scope (v1 supports company-financial claims), which sets expectations. It does not explicitly state when not to use it or list alternatives, but the context and limitations are clear enough for an agent.

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