iconify

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key traits: it's a query tool that interprets natural language, selects data sources automatically, and returns results. However, it doesn't mention potential limitations like rate limits, authentication needs, or error handling, leaving some behavioral aspects unspecified.

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

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

The description is front-loaded with the core functionality in the first sentence, followed by clarifying details and examples. Every sentence earns its place by explaining the tool's value proposition, usage instructions, and providing concrete examples without unnecessary repetition or 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?

Given the tool's complexity (natural language processing to select data sources) and lack of annotations or output schema, the description is mostly complete. It explains what the tool does, how to use it, and provides examples, but doesn't detail output formats or potential constraints like response time or data source limitations, which could be helpful for an agent.

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

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

The schema description coverage is 100%, with the parameter 'question' fully documented in the schema. The description adds minimal value beyond this, only reinforcing that questions should be in 'plain English' or 'natural language,' which is already implied by the schema's description. This meets the baseline for high schema coverage.

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

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

The description clearly states the tool's purpose: 'Ask a question in plain English and get an answer from the best available data source.' It specifies the verb ('ask'), resource ('answer'), and mechanism ('Pipeworx picks the right tool, fills the arguments'), distinguishing it from sibling tools like 'search_icons' or 'list_collections' which have different functions.

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 this tool: 'No need to browse tools or learn schemas — just describe what you need.' It provides clear alternatives by implying that other tools require browsing or schema knowledge, and includes examples like 'What is the US trade deficit with China?' to illustrate appropriate use cases.

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 behavioral details beyond annotations: it explains how the tool resolves the market, classifies the bet, fans out to specific packs based on the bet type, and returns an evidence packet plus comparison. 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 about six sentences long and well-structured: purpose, input types, processing logic, output, use cases, and value proposition. It is informative without being verbose, though minor redundancy (e.g., repeating 'core demo product') could be trimmed.

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

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

Given there is no output schema, the description adequately explains the return format ('evidence packet plus a simple market-vs-model comparison') and processing logic (classification, pack fan-out). It is complete for a tool of this complexity, though additional detail on the comparison metric would be helpful.

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

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

Schema coverage is 100%, and the description adds significant meaning: for 'market', it explains it can be a slug, URL, or question text; for 'depth', it adds context that 'quick' uses 2-3 sources and 'thorough' is full fan-out with default thorough. This enriches the schema 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: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It specifies the inputs (market slug, URL, or question text) and outputs (evidence packet and market-vs-model comparison). This distinguishes it from sibling tools like ask_pipeworx or compare_entities, which handle different types of queries.

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

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

The description explicitly lists use cases: 'Use for 'should I bet on X?', 'what does the data say about this Polymarket market?', or 'is there edge in this bet?'. It does not explicitly mention when not to use or alternatives, but the context of sibling tools implies this is for bet-specific research. The guidance is clear and actionable.

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

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

Discloses return type (paired data + URIs) and data sources (SEC EDGAR, FDA). Without annotations, it carries the full burden and does well, though it could mention that it is read-only and does not modify data.

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 that are front-loaded with purpose and contain no superfluous information. Every sentence provides 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 entity types, data fields, and efficiency. However, without an output schema, it lacks detailed return structure (e.g., JSON format, how URIs are presented), which would be helpful.

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?

Adds meaning beyond the 100% covered schema by providing examples for values (tickers/CIKs for company, drug names for drug) and clarifying the purpose of the parameters.

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 verb (compare) and resource (entities), distinguishes from siblings by noting it replaces 8-15 sequential calls, and specifies two entity types with their data 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 states when to use: for side-by-side comparison of 2-5 entities. Mentions efficiency gains but does not explicitly exclude single-entity queries or name alternatives like resolve_entity.

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

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

With no annotations provided, the description carries full burden. It describes the search behavior and return format (tools with names/descriptions), but doesn't disclose important behavioral traits like rate limits, authentication requirements, error conditions, or whether results are ranked by relevance. It adds some context but leaves gaps.

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

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

Two sentences, zero waste. First sentence states purpose and behavior, second provides crucial usage guidance. Every word earns its place, and the most important information (when to call first) is appropriately front-loaded.

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

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

For a search tool with 2 parameters and 100% schema coverage but no annotations or output schema, the description provides good context about purpose and usage. However, it doesn't explain what the return format looks like beyond 'tools with names and descriptions' - no details on structure, pagination, or error cases. The guidance is strong but output details are 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?

Schema description coverage is 100%, so the schema already fully documents both parameters. The description doesn't add any parameter-specific information beyond what's in the schema (query as natural language description, limit with default/max). Baseline 3 is appropriate when schema does the heavy lifting.

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

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

The description clearly states the tool's purpose with specific verbs ('search', 'returns') and resources ('Pipeworx tool catalog', 'most relevant tools with names and descriptions'). It distinguishes from siblings like get_icons, list_collections, and search_icons by focusing on tool discovery rather than icons or collections.

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

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

The description provides explicit guidance on when to use this tool ('Call this FIRST when you have 500+ tools available and need to find the right ones for your task'), including a specific threshold condition and clear alternative context (when overwhelmed by many 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?

No annotations are provided, so the description carries full burden. It transparently describes the multi-source aggregation behavior, output format (citation URIs), and current limitations (only company type). However, it does not disclose potential rate limits or authentication needs, though for a read-only tool this is acceptable.

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

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

The description is a single paragraph that front-loads the main purpose, then details data sources, then provides usage guidance. It is reasonably concise, though the repetition of 'Returns pipeworx:// citation URIs for everything' could be trimmed. Overall efficient.

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

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

Given no output schema and no annotations, the description sufficiently covers input parameters, data sources, output format, and alternative tools. The mention of replacing 10-15 sequential calls gives a strong sense of utility. It is fully adequate for agent decision-making.

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

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

Schema coverage is 100% with descriptions, but the description adds meaningful context beyond the schema: clarifies that 'type' only supports 'company' currently, and that 'value' expects ticker or zero-padded CIK, explicitly stating that names are not supported. This reduces ambiguity.

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

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

The description clearly states it returns a 'Full profile of an entity across every relevant Pipeworx pack in one call,' lists specific data types (SEC filings, revenue, patents, news, LEI), and differentiates from sibling tools like usa_recipient_profile. The verb 'returns' paired with the comprehensive scope makes the purpose unmistakable.

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

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

Explicitly says when to use (for comprehensive profile) and when not to ('For federal contracts call usa_recipient_profile directly'). Also advises to use resolve_entity first if only a name is available. This provides clear decision 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states this is a deletion operation, implying it's destructive, but doesn't specify whether deletions are permanent, reversible, require specific permissions, or have side effects (e.g., affecting related data). For a destructive tool with zero annotation coverage, this leaves significant behavioral gaps.

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

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

The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It's front-loaded with the core action ('Delete') and resource ('stored memory'), making it immediately scannable and zero waste.

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

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

For a destructive tool with no annotations and no output schema, the description is incomplete. It doesn't cover behavioral aspects like permanence, permissions, or error conditions, nor does it explain what happens after deletion (e.g., confirmation message, side effects). Given the complexity of a delete operation, more context 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?

The input schema has 100% description coverage, with the 'key' parameter fully documented in the schema itself. The description adds no additional parameter semantics beyond what's in the schema (e.g., format examples, constraints, or relationship to other tools). This meets the baseline for high schema coverage.

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

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

The description clearly states the action ('Delete') and the target resource ('a stored memory by key'), making the purpose immediately understandable. However, it doesn't explicitly differentiate this tool from its sibling 'recall' (which likely retrieves memories) or other memory-related operations, which would be needed for a perfect score.

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. It doesn't mention prerequisites (e.g., needing an existing memory key), when not to use it, or how it relates to sibling tools like 'remember' (store) or 'recall' (retrieve). The agent must infer usage from the name and description alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves data and returns specific fields (SVG body, width, height), which implies a read-only operation, but it does not disclose other behavioral traits such as error handling, rate limits, authentication needs, or whether it supports pagination for multiple icons. The description is minimal and misses key operational details.

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 sentence that efficiently conveys the tool's purpose, scope, and return values without any redundant information. It is front-loaded with the core action and resource, making it easy to understand quickly, and every part of the sentence adds value.

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

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

Given the tool's moderate complexity (2 required parameters, no output schema, and no annotations), the description is somewhat complete but has gaps. It covers what the tool does and returns, but lacks details on behavioral aspects like errors or limits. Without annotations or an output schema, the description should provide more context to fully guide usage, but it does the minimum viable job.

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, with clear documentation for both parameters (prefix and icons), including examples. The description does not add any additional meaning beyond what the schema provides, such as explaining parameter interactions or constraints. However, since schema coverage is high, the baseline score of 3 is appropriate, as the schema adequately handles parameter semantics.

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 specific action ('Retrieve'), resource ('SVG body data for one or more icons'), and scope ('in a specific collection'), distinguishing it from sibling tools like list_collections (which lists collections) and search_icons (which searches icons). It explicitly mentions what is returned ('SVG body, width, and height for each icon'), making the purpose 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?

The description implies usage by specifying 'in a specific collection' and the return format, but it does not explicitly state when to use this tool versus alternatives like search_icons. It provides some context (e.g., retrieving data for icons in a collection) but lacks clear guidance on exclusions or direct comparisons to sibling tools, leaving usage somewhat inferred.

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

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

With no annotations provided, the description carries full burden. It discloses the return format details (prefix, name, total icon count, author, license, category) which is valuable behavioral information. However, it doesn't mention potential limitations like pagination, rate limits, authentication requirements, or error conditions that would be important for a read operation.

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

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

The description is a single, well-structured sentence that efficiently communicates both the action and the return format. Every element serves a purpose with zero waste - it states what the tool does and what information it provides without unnecessary verbiage.

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 read-only tool with no parameters and no output schema, the description provides adequate coverage of the purpose and return format. However, without annotations or output schema, it could benefit from more behavioral context (like whether this returns all collections at once or if there are limitations). The description is complete enough for basic understanding but leaves some operational questions unanswered.

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 tool has zero parameters (schema coverage 100%), so the baseline is 4. The description appropriately doesn't discuss parameters since none exist, focusing instead on the return values and purpose. This is the correct approach for a parameterless tool.

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 specific action ('List all available icon collections'), identifies the resource ('icon collections in Iconify'), and distinguishes from sibling tools (get_icons and search_icons focus on individual icons rather than collections). It provides a comprehensive verb+resource+scope statement.

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

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

The description implies usage context by specifying what information is returned (prefix, name, count, etc.), but doesn't explicitly state when to use this tool versus the sibling tools. No explicit alternatives or exclusions are mentioned, though the different resource focus (collections vs icons) provides some implicit 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?

Discloses rate limit (5 messages per identifier per day) and hints at expected message style. No annotations provided, so description compensates adequately.

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 purpose, no wasted words. Efficient and scannable.

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

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

Covers purpose, usage, rate limit, and content guidelines. No output schema needed for a feedback tool. Missing details on response behavior but acceptable.

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

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

Schema has 100% coverage, but description adds meaningful guidance on message content (e.g., describe using tool terms, avoid verbatim prompts). Exceeds baseline of 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?

Clearly states 'Send feedback to the Pipeworx team' and lists specific use cases (bug reports, feature requests, missing data, praise). Distinct from all sibling tools.

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

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

Explicitly describes when to use and provides content guidance (do not include end-user prompt verbatim). Mentions rate limits but does not explicitly list when not to use.

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

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

The description details how the tool works (walks child markets, extracts dates/thresholds, sorts, reports violations) and what it returns. This adds operational context beyond the annotations (readOnly, openWorld, not destructive), which already signal a safe, non-destructive operation. 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 moderately long (4 sentences) but well-structured, starting with the core concept, then explaining the logic, and finally describing the output. It could be slightly more concise, but every sentence adds value.

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

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

Given the simple input (one parameter), no output schema, and helpful annotations, the description is complete. It explains the purpose, logic, and return format (list of entries with market_a, market_b, gap_pp, suggested_trade), 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% for the single 'event' parameter, so baseline is 3. The description adds context ('Pass a Polymarket event slug or URL; the tool walks the child markets') but does not significantly extend beyond what the schema's description 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 'Find arbitrage opportunities within a Polymarket event by checking for monotonicity violations.' It explains the specific condition (earlier market trading higher than later) and provides an example, making the purpose unambiguous and distinct from siblings 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 implicitly specifies when to use: for Polymarket events with multiple related markets (by date/threshold). It does not explicitly state when not to use or mention alternatives, but the context is clear enough for an AI agent to decide.

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

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

Adds significant behavioral details beyond annotations: groups by asset, fetches price history once, computes model probability, ranks by edge, returns suggested direction. Aligns with readOnlyHint=true.

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 informative and well-structured: main purpose, methodology, output, use case. Slightly verbose with technical detail but earns its place.

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

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

No output schema, but description explains returns top N with edge magnitude and suggested direction. Lacks explicit output fields but sufficient for understanding. Complexity moderate.

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

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

Input schema has 100% description coverage for all three parameters (limit, window, min_edge_pp) with defaults and constraints. The description does not add new parameter information, so baseline score applies.

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

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

The description clearly states it scans Polymarket markets and returns those with highest disagreement (edge), specifically for crypto-price bets using a lognormal model. It distinguishes from manual browsing and implies a focused scope.

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

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

The description provides context: 'Built for the what should I bet on today question' but does not explicitly mention when not to use or alternatives like polymarket_arbitrage or bet_research. Implicitly it's for opportunity discovery.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the dual functionality (retrieve by key vs. list all) and mentions persistence across sessions. However, it doesn't disclose important behavioral traits like error handling (what happens if key doesn't exist), authentication requirements, rate limits, or whether the operation is read-only (though implied by 'retrieve').

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 perfectly concise and well-structured. Two sentences cover all essential information: the first explains the dual functionality, the second provides usage context. Every word earns its place with zero redundancy or unnecessary elaboration.

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

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

Given the tool's moderate complexity (dual functionality, session persistence) and no annotations or output schema, the description is adequate but has gaps. It explains what the tool does and when to use it, but doesn't describe return formats, error conditions, or limitations. For a memory retrieval tool with potential cross-session persistence, more behavioral context would be helpful.

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 adds meaningful context about the single parameter beyond what the schema provides. The schema has 100% coverage with a clear description, but the description explains the semantic behavior: 'omit key to list all keys' and connects it to the tool's dual functionality. For a tool with only one parameter, this provides good additional guidance.

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 with specific verbs ('retrieve' and 'list') and resources ('previously stored memory by key' or 'all stored memories'). It distinguishes between retrieval and listing operations based on the presence of the key parameter. However, it doesn't explicitly differentiate from sibling tools like 'remember' or 'forget' beyond mentioning 'context you saved earlier'.

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

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

The description provides clear usage context: 'Use this to retrieve context you saved earlier in the session or in previous sessions.' It also explains when to use which mode: 'Retrieve a previously stored memory by key, or list all stored memories (omit key).' However, it doesn't explicitly mention when NOT to use this tool or name specific alternatives among siblings.

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

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

Without any annotations, the description carries the full burden of disclosing behavior. It explains the parallel fan-out to SEC EDGAR, GDELT, and USPTO, the return format (structured changes, total_changes count, pipeworx:// URIs), and accepted date formats. It does not mention potential failure modes, rate limits, or authentication needs, which would make it a 5, but it is still very informative.

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, consisting of two sentences plus a final usage note. It is front-loaded with the core purpose and efficiently provides necessary details without redundancy. Every sentence adds unique value, and the structure is logical.

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 (parallel fan-out, multiple data sources, multiple parameter formats), the description covers all essential aspects: the entity types accepted, date format options, output structure, and use cases. There is no output schema, but the description clearly explains what the tool returns. For a tool with 3 parameters and no output schema, this is a complete and self-contained description.

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?

All three parameters have schema descriptions, but the tool description adds significant context beyond that: it explains the behavior of the 'type' parameter (only 'company' supported), provides example values and usage for 'since' (ISO date or relative like '7d', '30d', '3m', '1y'), and clarifies that 'value' can be a ticker or zero-padded CIK. This extra information is highly valuable for correct invocation.

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: 'What's new about an entity since a given point in time.' It further details the behavior for type='company', including the parallel fan-out to multiple data sources. It distinguishes itself from siblings by mentioning use cases like 'brief me on what happened with X' and change-monitoring workflows, which sets it apart from static entity profiles or comparison 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 recommends using the tool for 'brief me on what happened with X' or change-monitoring workflows, providing clear context for when to use it. It does not explicitly state when not to use it or name alternative tools, but the context is strong enough for an agent to infer 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: the persistence differences between authenticated users ('persistent memory') and anonymous sessions ('last 24 hours'), and the tool's purpose for cross-tool context. It lacks details on error conditions or limits, but covers essential operational behavior.

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

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

The description is front-loaded with the core purpose in the first sentence, followed by usage guidance and behavioral details. Both sentences earn their place by providing essential information without redundancy, making it efficient and well-structured.

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

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

Given the tool's moderate complexity (2 required parameters, no output schema, no annotations), the description is mostly complete. It covers purpose, usage, and key behavioral traits like persistence. However, it lacks details on error handling or response format, which would be helpful for full completeness.

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

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

The schema description coverage is 100%, with both parameters ('key' and 'value') well-documented in the schema. The description does not add any meaningful semantic details beyond what the schema provides (e.g., it doesn't explain key constraints or value formatting), so it meets the baseline for high schema coverage without extra value.

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

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

The description clearly states the specific action ('Store a key-value pair') and resource ('in your session memory'), distinguishing it from sibling tools like 'recall' (which likely retrieves) and 'forget' (which likely deletes). It provides concrete examples of what can be stored ('intermediate findings, user preferences, or context across tool calls'), making the purpose 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?

The description explicitly states when to use this tool ('to save intermediate findings, user preferences, or context across tool calls'), providing clear context. However, it does not specify when not to use it or mention alternatives like 'recall' for retrieval or 'forget' for deletion, which would be needed for a perfect score.

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

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

No annotations provided, so description carries full burden. Discloses return values (ticker, CIK, company name, resource URIs) and that it uses a single call. Lacks details on error handling or rate limits, but covers core behavior well.

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

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

Two concise sentences with a natural list, front-loading the main purpose. Every sentence adds value with no redundancy.

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

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

No output schema, but description explains return values. Covers version limitation (v1 only company). Tool is simple with 2 required params; description is complete for its 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?

Schema coverage is 100%. Description adds examples (AAPL, 0000320193, Apple) and clarifies acceptable inputs for the type and value parameters, going beyond basic 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?

Clear verb (resolve), resource (entity to canonical IDs), and context (across Pipeworx data sources in a single call). Distinguishes from sibling tools like ask_pipeworx by specifying a unique resolution function.

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

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

Explicitly states it replaces 2–3 lookup calls, guiding when to use. Mentions v1 limitation to company type. Does not discuss when not to use or alternatives, but context is sufficient.

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

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

With no annotations provided, the description carries full burden. It discloses the return format ('prefix:name' format) which is valuable behavioral context, but does not mention rate limits, authentication needs, pagination behavior, or error handling. The description adds some value but leaves significant behavioral aspects unspecified.

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 with zero waste: first sentence states purpose and scope, second sentence specifies return format with a concrete example. Perfectly front-loaded and appropriately sized for this tool's complexity.

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 annotations and no output schema, the description provides adequate purpose and return format but lacks details about error conditions, rate limits, authentication requirements, and result structure beyond naming format. For a search tool with 2 parameters, this is minimally complete but has clear 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 description coverage is 100%, so the schema already documents both parameters thoroughly. The description adds no additional parameter semantics beyond what the schema provides, such as search algorithm details or result ordering. Baseline 3 is appropriate when schema does the heavy lifting.

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

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

The description clearly states the specific action ('Search for icons by keyword') and resource ('across all Iconify collections'), and distinguishes from sibling tools by focusing on keyword-based search rather than retrieval (get_icons) or collection listing (list_collections).

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

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

The description implicitly suggests usage for keyword-based icon searches, but does not explicitly state when to use this tool versus alternatives like get_icons or list_collections. It provides clear context about searching across collections but lacks explicit exclusions or named alternatives.

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

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

With no annotations provided, the description fully discloses behavioral traits: it validates claims using SEC EDGAR and XBRL, returns a verdict with structured output, actual value with citation, and percent delta. It also notes the version and scope limitations, providing comprehensive 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 extremely concise: three sentences covering purpose, scope, and benefits with zero redundancy. Information is front-loaded, with the core action in the first sentence.

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

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

Despite lacking an output schema, the description thoroughly explains the return types (verdict, structured form, actual value, citation, delta) and justifies the tool's existence. For a simple tool with one parameter, the context is complete and 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?

The single parameter 'claim' is well-described in the schema with examples. The description adds context about how the claim is processed (NL parsing, entity resolution) and what the output includes, enhancing the semantic understanding beyond the schema.

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

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

The description clearly states the tool's purpose: fact-checking natural-language claims against authoritative sources. It specifies the supported domain (company-financial claims for public US companies via SEC EDGAR and XBRL) and lists the types of verdicts returned, making the purpose very specific and distinguishable from siblings.

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

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

The description provides clear context on when to use the tool (for factual claims, especially company-financial) and highlights its value in replacing multiple sequential agent calls. However, it does not explicitly state when not to use it or compare it directly with sibling tools like 'ask_pipeworx'.

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