Cdec Ca

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

Beyond annotations (readOnlyHint, openWorldHint), the description reveals it routes to multiple tools, fills arguments, and returns structured answers with stable citation URIs, providing substantial behavioral insight.

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 thorough and front-loads key directives, but could be slightly more structured (e.g., bullet points) for easier scanning. Still, each sentence serves a purpose.

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

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

Given the simple input schema and no output schema, the description fully covers purpose, usage, behavior, and output format (structured answer with citations), leaving no critical 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?

Although schema coverage is 100% and the parameter description is minimal, the main description adds semantic guidance on the types of questions to ask, enhancing the parameter'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 answers factual questions using authoritative structured data, lists specific domains (SEC filings, FDA data, etc.), and provides examples, making its purpose and scope highly 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 advises preferring over web search and gives concrete when-to-use guidance with examples. However, it does not mention when to avoid or specify alternative sibling tools, slightly limiting differentiation.

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

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

Adds rich behavioral context: resolving the market, classifying the bet type, fanning out to appropriate packs (e.g., 'crypto+fred+gdelt for a BTC bet'), and returning an evidence packet with comparison. Annotations (readOnlyHint, openWorldHint, destructiveHint) are consistent, and the description explains the internal fan-out logic.

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 purpose, then covers input, behavior, and usage. It is comprehensive without being overly verbose, though slightly long. Each sentence contributes value, earning a 4.

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 clearly explains the return: 'an evidence packet plus a simple market-vs-model comparison.' It also details the classification categories and fan-out examples, making the tool's behavior self-contained and understandable.

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

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

Schema description coverage is 100%, so the baseline is 3. The description reiterates the three input types for 'market' (slug, URL, question) and the 'depth' enum meanings, but adds no additional meaning beyond what the schema already provides.

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

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

The description clearly states the tool's purpose: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It specifies the inputs (slug, URL, question) and outputs (evidence packet, market-vs-model comparison). It distinguishes itself from sibling tools by noting it's the 'core demo product' and saves agents from discovering packs themselves.

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: 'Use for "should I bet on X?", "what does the data say about this Polymarket market?", or "is there edge in this bet?".' It also implies when not to use (if you want direct pack access) by highlighting its fan-out behavior.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context beyond that, such as the data sources (SEC EDGAR/XBRL, FAERS, FDA) and return format (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 concise at around 6 sentences, front-loading the core purpose. It could be slightly more structured but remains clear and efficient without extraneous content.

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 explains returns as 'paired data + citations URIs,' which is sufficient for typical usage. It covers the main use cases and data types, providing adequate completeness for a list tool with good annotations.

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

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

Schema descriptions cover both parameters fully (100% coverage), so baseline is 3. The description adds extra meaning by detailing what fields are pulled for each type (e.g., revenue, net income for company; adverse events for drug), enhancing understanding beyond the enum and string 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 compares 2–5 companies or drugs side by side in one call. It specifies the verb 'compare' and the resources (companies, drugs), distinguishing it from sibling tools like entity_profile or validate_claim.

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

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

The description provides explicit user phrasing examples ('compare X and Y', 'X vs Y', etc.) and notes it replaces 8–15 sequential calls, guiding when to use it. However, it does not mention when not to use or name specific alternative 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?

While annotations indicate read-only behavior, the description adds no extra behavioral context such as the aggregation level (daily), time range behavior, or what data is returned. There is a missed opportunity to clarify that the tool returns daily aggregated measurements.

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 at the cost of insufficient information. It is front-loaded but does not earn its place by providing meaningful guidance.

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, 4 parameters (3 required), and a 25% schema coverage, the description is severely incomplete. It fails to explain return values, parameter formatting (except start), time zone, or pagination, leaving the agent ill-equipped 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?

With only 25% schema description coverage (only start has format hint), the description adds no semantic value for parameters. It merely names station and sensor without explaining their roles or formats 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 'Daily data for (station, sensor).' is a tautology that merely restates the tool name and parameters without specifying an action (e.g., retrieve, list). It does not distinguish it from sibling tools like hourly_data or event_data, leaving the purpose ambiguous.

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 such as hourly_data or latest. The description lacks context for appropriate usage scenarios or prerequisites.

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. Description adds that it returns 'top-N most relevant tools with names + descriptions,' clarifying behavior beyond annotations. 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?

Description is well-structured with a clear first sentence, domain list, result format, and usage tip. Slightly verbose but every sentence adds value, earning a 4.

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

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

Despite no output schema, the description fully explains what the tool returns, how to use it, and provides examples. It is complete for the tool's purpose.

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 covers both parameters with descriptions. The description adds context like 'top-N' and examples for query, but does not significantly exceed schema coverage, rating a baseline 3.

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

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

The description clearly states the tool finds tools by describing data or task, listing specific domains. It distinguishes itself from sibling tools as a meta-discovery tool, explicitly advising to call it first.

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

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

Provides explicit guidance: 'Call this FIRST when you have many tools available and want to see the option set.' Includes examples of queries, making usage very 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?

Lists exact returned data (SEC filings, fundamentals, patents, news, LEI) and mentions citation URIs. Annotations already indicate read-only, 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?

Six sentences, front-loaded with purpose, includes examples and constraints, no redundant information.

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

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

Thoroughly describes return value for a complex aggregation tool without output schema. Covers all key aspects of usage and 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 covers 100% of parameters with descriptions. Description adds context like zero-padded CIK example and reinforces that names need resolve_entity, adding value 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 'Get everything about a company in one call' and provides specific user queries that trigger it. Distinguishes from siblings by noting it replaces 10+ pack tools 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 (e.g., 'tell me about X') and when not to (names not supported, use resolve_entity first). Provides clear context for selection.

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 destructiveHint=false. Description adds no behavioral details (e.g., rate limits, data volume, filtering). The phrase 'event-based irregular data' does not clarify behavior 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?

Too brief to be informative. A single phrase without sentences. While short, it fails to convey necessary information, so it's not effective 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 0% schema coverage, no output schema, and 4 parameters, the description is severely incomplete. It provides no context for how to use the tool or what results 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?

With 0% schema description coverage, the description must compensate but does not. It mentions no parameters. The input schema has 4 properties (station_id, sensor, start, end) but the description gives no meaning or usage hints for them.

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 'Event-based irregular data' is a noun phrase that doesn't specify an action (retrieve, list, etc.). It vaguely describes the data type but not the tool's function. Sibling tools like daily_data and hourly_data suggest data retrieval, but no 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?

No guidance on when to use this tool versus alternatives such as daily_data, hourly_data, or latest. No when-to-use or when-not-to-use information.

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 confirms destructive action (delete) consistent with destructiveHint=true annotation. Adds context about clearing sensitive data, but no details on irreversibility or side effects 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?

Three lean sentences: action, usage guidance, sibling references. 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 annotations, the description covers purpose, usage, and associations. Lacks explicit mention of permanent deletion, but destructiveHint covers it.

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

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

Schema coverage is 100% with clear description for the key parameter. Description adds only 'by key', reinforcing schema. Does not exceed baseline 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 specifically states 'Delete a previously stored memory by key', clearly identifying the verb, resource, and method. It also contrasts with sibling tools remember and recall.

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

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

Provides explicit when-to-use scenarios: stale context, task completion, clearing sensitive data. Does not explicitly state when not to use, but references alternatives (remember/recall) implicitly.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds no additional behavioral insights such as pagination, data volume, or authorization needs.

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?

While brief, the description is under-specified. It does not earn its place as it provides minimal value. True conciseness would include essential context in few words, but here key information is missing.

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 tool description fails to describe what data is returned, such as time granularity, date range behavior, or units. The tool is about hourly data but leaves agents guessing about the response format and scope.

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

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

With 0% schema description coverage, the description provides no help for the 4 parameters (station_id, sensor, start, end). It does not explain format, constraints, or purpose beyond what is minimally inferred from names.

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 'Hourly data.' is extremely vague, essentially a tautology. It does not specify what operation is performed (e.g., fetch, list) nor does it distinguish from sibling tools like 'daily_data' or 'event_data'.

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

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

No guidance on when to use this tool versus alternatives. Lacks any context for when it is appropriate, prerequisites, or exclusions.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds no behavioral context beyond the tool name. It does not explain data freshness, rate limits, or any other behavioral traits.

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?

While extremely concise (two words), it is underspecified to the point of being unhelpful. Conciseness should not sacrifice necessary detail.

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

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

Given two required parameters with no schema descriptions, no output schema, and related sibling tools, the description is completely inadequate. It fails to explain what 'latest value' means in the station/sensor context.

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

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

With 0% schema description coverage, the description should compensate by explaining the parameters (station_id, sensor), but it provides no explanation at all.

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 'Latest value.' is vague; it does not specify what resource or entity the tool retrieves the latest value of. It barely differentiates from siblings like daily_data or hourly_data.

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

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

No guidance on when to use this tool vs alternatives such as daily_data or station_info. No context about prerequisites or limitations.

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 operation) but provide no other behavioral details. The description adds significant context: the tool is free, does not count against tool-call quota, is rate-limited, digests are read daily, and feedback directly influences roadmap. This clarifies expectations beyond the annotations.

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

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

The description is a single paragraph that front-loads the purpose and use cases. It is efficient, with every sentence adding value. Minor improvement could be using bullet points for clarity, but current structure is concise and well-organized.

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 (one with enum, one nested object), no output schema, and no sibling overlaps, the description is comprehensive. It covers all usage scenarios, constraints, and outcomes, leaving no ambiguity for the agent.

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

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

Schema coverage is 100% with field descriptions. The description adds usage guidance on how to structure the message (e.g., be specific, 1-2 sentences, 2000 char max) and explains the 'context' field purpose (optional, linked to tools/packs). This enriches the schema without redundancy.

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 provide feedback on broken, missing, or desired functionality. It enumerates specific use cases (bug, feature, data_gap, praise) that directly differentiate it from sibling tools, which are primarily data retrieval and analysis 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 specifies when to use each feedback type (e.g., 'bug' for wrong data, 'feature' for missing capabilities). It provides actionable constraints: describe in terms of Pipeworx tools/packs, avoid pasting user prompts, and notes rate limits (5 per identifier per day) and quota-free usage.

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 about returning ranked opportunities with trade direction and reasoning, complementing the annotations without contradiction.

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

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

The description is informative and well-structured, front-loading the purpose and mode details. While slightly long, every sentence contributes value. Could be marginally more concise but remains effective.

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

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

Given the tool's complexity (two modes, arbitrage detection) and no output schema, the description adequately explains the return value (ranked opportunities with reasoning). It covers the main functionality without excessive detail.

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 tool description adds value beyond the schema, specifying that event accepts slug or full URL and explaining the cross-event behavior for the topic parameter.

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

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

The description clearly states the tool finds arbitrage opportunities on Polymarket by checking monotonicity violations, and distinguishes two modes (event and topic) with specific explanations. This differentiates it from sibling tools like polymarket_edges.

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

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

Explicitly describes when to use each mode: event mode for a single event slug, topic mode for cross-event related markets. Provides an example of why topic mode is necessary, offering clear guidance on appropriate usage.

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

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

Description adds significant context beyond readOnlyHint/openWorldHint/destructiveHint annotations: explains V1 covers crypto-price bets with lognormal model from FRED and live coinpaprika price, the process (scans top markets, groups by asset, computes probability, ranks by edge), and output (suggested trade direction). 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?

Description is moderately long but well-structured: starts with purpose, explains methodology, then output. Every sentence adds value, though could be slightly more concise without losing detail.

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

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

Given the complexity (scanning, grouping, computing model probability), the description adequately covers behavior and return value (ranked edges with direction). No output schema, so description fills the gap well.

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

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

Schema already provides 100% description coverage for all three parameters. The description reiterates usage context but doesn't add new semantic details beyond what the schema offers. Baseline 3 is appropriate.

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

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

Description clearly states the tool scans high-volume Polymarket markets and returns those where Pipeworz data disagrees with market price. It specifies the verb (scan, return), resource (Polymarket markets), and unique value (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?

Description explicitly says it's built for the 'what should I bet on today' question, guiding agents to discover opportunities without manual browsing. It doesn't explicitly state when not to use, but the context is clear enough for appropriate 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 and destructiveHint=false, indicating safe read-only behavior. The description adds context about scope (identifier-based) and relationships to remember/forget. No contradictions. However, it does not specify behavior when a key does not exist (e.g., returns null or error).

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

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

The description is concise at three sentences, with the main verb 'Retrieve' first. It is well-structured, front-loading the core behavior and then elaborating with examples and pairing advice. 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?

Given the tool's simplicity (one optional parameter, no output schema, rich annotations), the description covers core functionality, scope, and tool relationships. It lacks explicit failure handling details but is otherwise 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?

The input schema has 100% description coverage for the sole parameter 'key', explaining it as the memory key to retrieve or omit to list all keys. The description repeats this and adds usage context but does not add new semantic meaning 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 tool retrieves a value saved via remember or lists all saved keys when the key argument is omitted. It provides specific use cases (ticker, address, notes) and distinguishes from sibling tools (remember and forget) by mentioning pairing with 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?

The description explains when to use the tool (to look up context stored earlier) and notes it is scoped to an identifier. It also advises pairing with remember and forget. However, it lacks explicit guidance on when not to use it or alternatives among other siblings like entity_profile or daily_data.

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. The description adds that it fans out to three external sources in parallel and returns structured changes with URIs, disclosing key behaviors 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, front-loaded with the purpose, and every sentence contributes essential information without redundancy. It effectively communicates key details in a compact form.

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

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

Despite no output schema, the description explains the return structure (structured changes, total_changes count, citation URIs). It covers complexity of parallel fan-out, parameter formats, and typical use cases, leaving no critical gaps.

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

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

Schema coverage is 100%, so the description is not required to add much, but it does provide helpful examples for the 'since' parameter (ISO date and relative shorthand) and suggests typical defaults like '30d' or '1m', adding 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 defines the tool as answering "What's new with a company?" with specific query examples. It specifies the resource (company) and action (aggregating recent changes from SEC, GDELT, USPTO), distinguishing it from siblings like daily_data or latest.

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 patterns with natural language queries, making it easy for an agent to identify when to invoke this tool. It does not explicitly list when not to use, but the examples are sufficient for typical scenarios.

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

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

Discloses scoping by identifier, persistence for authenticated users, and 24-hour retention for anonymous sessions. Adds 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?

Four sentences with clear front-loaded purpose. No fluff, every sentence adds value.

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

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

Covers purpose, when to use, pairing, retention policy, and parameter hints. No gaps given the tool's simplicity.

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

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

Schema already provides descriptions for key and value. Description adds example keys and clarifies value can be any text, adding slight 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?

Clearly states the tool saves data for reuse across conversations or sessions. Distinguishes from siblings by mentioning recall 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 tells when to use (discover worth-carrying info), and pairs with recall and forget. Differentiates persistent vs. anonymous memory.

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, destructiveHint=false, and openWorldHint=true. The description adds 'snapshots' but does not clarify behavioral traits like data freshness, pagination, or whether partial results are possible.

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 (two words) but this brevity sacrifices clarity. Important contextual information is omitted, making it ineffective despite its short length.

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

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

With no output schema and a single optional parameter, the description should clarify what data is returned (e.g., current storage levels per station, time of snapshot). The omission leaves the agent underinformed.

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 sole parameter 'station_id' has no schema description (0% coverage), and the description does not explain its function (e.g., filtering by station). The agent receives no help understanding the parameter's role.

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 'Reservoir storage snapshots.' vaguely indicates it retrieves reservoir storage data, but it lacks specificity on temporal scope or format, and does not differentiate from sibling tools like 'daily_data' or 'latest' that might provide similar storage information.

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 provided on when to use this tool versus alternatives. With many data-oriented siblings, the agent lacks context for selection.

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 destructiveHint=false. The description adds that it returns IDs plus pipeworx:// citation URIs. While it doesn't discuss rate limits or edge cases, it provides sufficient 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 single, well-structured paragraph. It front-loads the purpose and follows with usage guidance and examples. Every sentence adds value without unnecessary verbosity.

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

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

Given no output schema, the description explains what the tool returns (IDs plus citation URIs). It covers usage, examples, and integration with other tools. The description is self-contained and provides all needed context for an AI agent.

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

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

Schema description coverage is 100% (both parameters described). The description adds value by explaining the meaning of parameter values (e.g., 'For company: ticker (AAPL), CIK (0000320193), or name') and giving examples, which enhances the schema's definitions.

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

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

The description clearly states that the tool looks up canonical/official identifiers for companies or drugs, with specific ID systems (CIK, ticker, RxCUI, LEI). It provides examples like 'Apple → AAPL / CIK 0000320193' and 'Ozempic → RxCUI 1991306'. This distinctly separates it from sibling tools such as entity_profile or compare_entities.

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

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

The description explicitly says 'Use this BEFORE calling other tools that need official identifiers' and notes it 'Replaces 2–3 lookup calls.' This provides clear guidance on when to use the tool and its role in a workflow.

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, but the description adds no additional context about response format, pagination, or data limits. For a metadata tool, behavioral traits like caching or freshness are not mentioned.

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 only two words, which is too short to be useful. It lacks front-loaded key information such as what the tool returns or the nature of the metadata.

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 single parameter, lack of output schema, and minimal annotations, the description is severely incomplete. An AI agent cannot determine correct input format, expected output, or how this tool fits into a workflow.

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 a required 'station_id' with no description, and the description fails to explain what a valid station_id looks like (e.g., numeric, string format). With 0% schema description coverage, the description must compensate but does not.

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 'Station metadata' is a vague phrase that restates the name without specifying a verb or the scope of metadata. It does not differentiate the tool from siblings like 'daily_data' or 'hourly_data', which likely also involve station data.

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

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

No guidance on when to use this tool versus alternatives. The sibling list includes many data retrieval tools, but the description offers no criteria for choosing 'station_info' over others.

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

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

The description adds behavioral details beyond annotations: it specifies the return structure (verdict types, extracted form, actual value with citation, percent delta) and the source (SEC EDGAR+XBRL). Annotations already declare readOnlyHint=true and openWorldHint=true, which align with the read-only verification nature. 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 three sentences, each serving a distinct purpose: stating the overall function, specifying when to use with examples, and detailing capabilities and outputs. It is front-loaded with the key action and resource, with no superfluous 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 single parameter and lack of output schema, the description is complete. It explains what the tool does, when to use, what it returns, and its limitations (v1 scope). The return structure is fully described, compensating for the absence of an output schema.

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

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

Schema coverage is 100%, and the schema description for the 'claim' parameter is already clear. The tool description reinforces understanding by providing examples of natural-language factual claims, adding value beyond the schema by clarifying the expected format and scope.

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

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

The description clearly states the tool's purpose: fact-checking natural-language claims against authoritative sources. It uses specific verbs like 'validate', 'verify', 'confirm/refute', and distinguishes it from siblings by focusing on factual claim verification, particularly for company-financial data via SEC EDGAR and XBRL.

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 ('when an agent needs to check whether something a user said is true') and provides example query patterns. It implies when not to use by noting the limitation to company-financial claims for v1, and highlights efficiency gains (replaces 4–6 sequential calls), offering good usage context.

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