Openreview

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive. The description adds beyond that: default model choice, cost implications (free vs. BYO key), and the return structure. It does not contradict annotations and provides useful behavioral context.

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 four sentences, each serving a purpose: purpose and scoring, model options, return format, use cases. No wasted words, front-loaded with the core action.

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

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

Given the tool has 4 parameters and no output schema, the description explains the return structure (per-model and combined) and use cases. It could mention error handling or behavior when the API key is missing but anthropic is requested, but overall it's sufficient for most agents.

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

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

Schema coverage is 100%, so the schema already documents all parameters. The description adds value by explaining default behavior for 'models', clarifying the API key arrangement, and providing an example for 'context'. This goes beyond the schema alone.

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: 'Probe one or more LLMs for what they know about a business/brand/product/topic and score visibility (0-100) per model.' It uses specific verbs and resources and distinguishes from sibling tools like scan_competitor_ai_presence by focusing on scoring and combining models.

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 for when to use the tool ('AI-marketing audits, pre-launch brand checks, competitive monitoring') but does not explicitly state when not to use it or mention alternatives among siblings. There is no comparison to related tools like scan_competitor_ai_presence.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context beyond annotations, such as routing to many tools, filling arguments, and returning pipeworx:// citation URIs. It does not contradict annotations.

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

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

The description is verbose, containing multiple paragraphs with examples and alternative tool details. While front-loaded with the key message, it could be more concise. Every sentence adds value, but the length may reduce readability.

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

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

Given the complexity of the tool (routing to 4482 sources), the description is comprehensive. It covers purpose, usage, examples, and alternatives. No output schema exists, but the description notes returned structured answers with citation URIs, providing sufficient 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?

Schema coverage is 100%, so baseline is 3. The description does not add significant additional meaning beyond the schema's aliases and examples. The examples illustrate usage but do not enhance parameter semantics 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 routes questions to 4482 tools and returns structured answers with citations. It explicitly says 'PREFER OVER WEB SEARCH' and gives specific domains (SEC filings, FDA drugs, etc.), distinguishing it from generic search and sibling tools like deep_research.

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: use for most factual questions, step up to ask_pipeworx_grounded for hallucination-resistant answers or deep_research for broad multi-part queries. Gives examples of when to use and what tools to use instead, meeting the 'when/when-not/alternatives' criteria.

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, openWorldHint, idempotentHint, destructiveHint. Description adds critical behavioral context: it routes among 4,482 tools, extracts answer only from tool result, returns explicit refusal reasons, and costs one extra LLM call. 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 fairly long but well-structured and front-loaded with the key value proposition. Every sentence adds meaningful information. Slightly verbose but justified by the 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?

Despite lack of output schema, the description fully specifies the return structure including fields like answer, evidence, confidence, and refusal reasons. It covers input, behavior, output, and usage boundaries, making the tool understandable without additional 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?

Schema covers 100% of parameters (all aliases for 'question'). Description adds that the question is in natural language, which is already implied by the schema. Baseline 3 is appropriate since description adds little beyond schema.

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

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

The description clearly states the tool's purpose: a hallucination-resistant answer mode that extracts answers only from tool results, returning a structured response with evidence. It distinguishes from sibling 'ask_pipeworx' by noting the extra LLM call and use case for high-stakes reads.

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 answers that will be quoted, cited, or acted on, especially in high-stakes domains like financial, legal, medical. Also advises to prefer 'ask_pipeworx' for casual lookups, providing clear when-not-to-use guidance.

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

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

The description massively exceeds the annotations, which already indicate readOnly, idempotent, and non-destructive behavior. It details the fan-out process, classifiers, response shapes, resolver contracts, parent event extraction, news fallback mechanisms, safety checks for low-confidence matches and closed markets, spread warnings, and resolution-rule risk. This comprehensive disclosure ensures agents understand all behavioral nuances.

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

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

The description is very long and dense, containing multiple paragraphs and structured sections (CLASSIFIERS, FAN-OUT EXAMPLES, etc.). While it is well-organized and front-loaded with the main purpose, the amount of detail could be streamlined. It is not concise, but the structure helps readability. Score 3 balances comprehensiveness against brevity.

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

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

Despite lacking an output schema, the description fully compensates by specifying response shapes (market, analysis, evidence, parent_event, news fields), resolver contract details, and safety mechanisms. It covers all aspects needed for an agent to understand and use the tool effectively, even for complex scenarios.

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. However, the description adds significant context beyond parameter descriptions: it explains the 'depth' parameter with examples (quick vs thorough), details the 'market' input types (slug, URL, question), and describes the effect of 'include_raw' on response size. This additional meaning justifies a score of 4.

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

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

The description opens with 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call', which is a specific verb+resource combination. It clearly states the tool's core function and distinguishes it from sibling tools like polymarket_edges or polymarket_arbitrage by describing its unique data aggregation approach.

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 use cases: 'Use for 'should I bet on X', 'what does the data say about Y', or 'is there edge in Z''. This gives clear context for when to use the tool. However, it does not specify when not to use it or explicitly rule out alternatives, which would have earned a 5.

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

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

Annotations provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds substantial behavioral context: data sources (SEC EDGAR/XBRL for companies, FAERS for drugs), handling of off-calendar fiscal years, sorting by primary metric, and return format (paired data + citation URIs). No contradiction with annotations.

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

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

The description is relatively long but every sentence earns its place, starting with natural language triggers, then detailing data sources and special features. Could be slightly more structured (e.g., bullet points), but it is not verbose and front-loads key purpose.

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

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

Given no output schema, the description only vaguely mentions 'paired data + pipeworx:// citation URIs'. It does not detail the response structure or explain how results are sorted beyond 'by primary metric'. More output detail would improve completeness for an AI agent interpreting results.

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

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

Schema coverage is 100%, but the description adds meaning beyond the schema: it explains the natural language triggers, provides examples for values (e.g., tickers/CIKs for companies, drug names), and clarifies what data each type pulls. This enriches the schema's bare enum and array descriptions.

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

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

The description clearly states the tool's purpose: side-by-side comparison of 2-5 companies or drugs. It provides specific natural language triggers ('Compare X and Y', 'X vs Y', etc.) and distinguishes from siblings like entity_profile by emphasizing parallel lookups over sequential ones.

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 includes 'ALWAYS PREFER over sequential single-pack lookups when comparing entities' and notes it replaces 8-15 sequential lookups, giving clear context for use. However, it lacks explicit when-not-to-use guidance or alternatives beyond this preference.

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 beyond annotations: parallel decomposition, output format (findings packet with citations and gaps), expected latency (15-60s), and that it is not open-web search. No contradiction 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?

Well-structured and front-loaded with critical info (account, alternative), though slightly long at 150 words. Every sentence adds value without redundancy.

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

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

Complete for a research tool: covers account requirement, input guidance, process explanation, output description, limitations (breaking news gaps), and expected time. Compensates for lack of 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% (baseline 3), but description adds explanatory detail: depth enum values correspond to facet counts (3,5,8), default is 'standard', and thorough requires paid plan. Question parameter emphasized as suitable for broad questions.

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 performs multi-source structured research across 1129 data sources in one call, distinguishing it from siblings like ask_pipeworx for single lookups and for breaking news.

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 (broad/multi-part questions over structured data) and when not to use (breaking news, current events, single lookup), with named alternatives (ask_pipeworx). Also mentions account requirements.

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 idempotentHint=true, indicating safe, non-destructive behavior. The description adds that results are ready to call directly with curated examples and no second schema lookup needed, providing useful behavior 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 well-structured, front-loaded with purpose and usage. It lists many domains, which is helpful but adds length. Could be slightly more concise, but 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 6 parameters (1 required) and no output schema, the description compensates by explaining the output format (names, descriptions, full schemas with examples) and when to call the tool. Completeness is adequate for discovery use.

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

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

Schema coverage is 100% (all parameters have descriptions). The description mentions the query parameter and its aliases, but this is already detailed in the schema. No additional parameter semantics 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's purpose: 'Find tools by describing the data or task.' It lists specific domains (SEC filings, FDA drugs, etc.) and explains it returns the top-N relevant tools with full schemas, distinguishing it from sibling tools like deep_research or search_notes by instructing to call it first when exploring options.

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

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

The description provides clear usage guidance: 'Use when you need to browse, search, look up, or discover what tools exist for...' and 'Call this FIRST when you have many tools available and want to see the option set.' However, it does not explicitly state when not to use it.

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

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

Annotations already declare readOnly, openWorld, idempotent, non-destructive. Description adds context about fanning across multiple sources, return fields, patents API sunset with soft-fail, and fallback chains. 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 longer but well-structured with front-loaded example queries and bullet-like details. Every sentence adds value; slight verbosity warranted by 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?

No output schema, but description details all returned fields (cik, filings, fundamentals, patents, news, LEI) with caveats. Sufficient for an agent to understand the tool's output and integrate 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 descriptions. Description adds valuable context: value must be ticker or zero-padded CIK, names need resolve_entity first. This goes beyond schema.

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

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

The description clearly states the tool provides a 'full cross-source profile of a US public company' with specific example queries. It distinguishes itself from chaining single-pack lookups and lists outputs and sources, making the purpose unmistakable.

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

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

Explicitly says 'ALWAYS PREFER over chaining single-pack... when user asks for a holistic view' and notes 'Names not supported — use resolve_entity first'. Clear when-to-use and 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?

Annotations already mark destructiveHint=true and idempotentHint. The description adds useful behavioral context: 'clear sensitive data' and 'stale context', enriching understanding 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?

Two sentences, zero waste. Action stated first, then usage guidance. Perfectly concise 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?

For a simple tool with one required parameter and no output schema, the description fully covers purpose, usage, and pairing with siblings. No 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 baseline 3. Description adds slight nuance ('previously stored' implying key must exist) but doesn't significantly enhance parameter 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 explicitly states 'Delete a previously stored memory by key' – a specific verb (delete) and resource (memory). It distinguishes from siblings 'remember' and 'recall' by mentioning pairing.

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

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

Provides clear when-to-use scenarios: 'when context is stale, the task is done, or you want to clear sensitive data'. Also suggests pairing with siblings, implying alternatives, though no explicit when-not-to.

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 explains fetching, extracting title/description/links, and output format. Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint) align; description adds detail beyond them.

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

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

Two sentences plus a list of use cases. Efficient, front-loaded with action and output. Could be slightly more structured but no waste.

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

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

With 2 parameters and no output schema, description fully explains input, process, and output format. Annotations cover safety and idempotency. Complete for 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 coverage is 100% with descriptions for both parameters (url, max_links). Description adds no extra meaning beyond schema; baseline 3 is appropriate.

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

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

The description clearly states the tool generates a production-ready llms.txt file for any URL, specifying the verb 'Generate', the resource 'llms.txt file', and context. It distinguishes from siblings as no other tool does this.

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 use cases: getting a client's site indexed, drafting for own project, auditing competitors. No explicit when-not-to-use or alternatives, but sibling list shows no close overlap.

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, openWorldHint, idempotentHint, and destructiveHint, which comprehensively cover behavioral expectations. The description adds minimal extra context by noting the note type variety but does not introduce or contradict any 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?

Extremely concise at 5 words, a single sentence fragment. It is front-loaded and free of fluff, but it could be slightly more structured (e.g., a complete sentence) while still being concise.

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

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

Given the presence of output schema and rich annotations, the description is minimally adequate. It identifies the tool's purpose but does not explain return values or pagination (though pagination is unlikely for a single note). More context about the return structure could help, but overall completeness is 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?

Input schema has 100% description coverage, with clear descriptions for both 'id' and 'details'. The tool description does not add further parameter semantics beyond what the schema provides, so a baseline score of 3 is appropriate.

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

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

The description clearly states the resource ('note') and provides examples of note types (paper, review, comment, decision), giving a good sense of what the tool returns. However, it does not explicitly distinguish from sibling tools like get_paper or search_notes, though the context implies a single note retrieval by ID.

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 get_note versus alternatives (e.g., search_notes for multiple notes, get_paper for paper-specific details). The description does not mention prerequisites or context, leaving the agent to infer usage through tool name and schema.

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, openWorldHint, idempotentHint true, destructiveHint false, so the safety profile is clear. The description adds that the tool returns the paper and all child notes, providing context beyond annotations. It does not detail error behavior or rate limits, but 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 two sentences with no extraneous information. The first sentence front-loads the tool's output, and the second states the input. Every word is earned.

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 tool with one required parameter and an output schema (not shown), the description is fairly complete. It covers what the tool returns and the input needed. Minor gaps: no mention of error handling or behavior when forum_id is invalid or paper has no children, but these are not critical.

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

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

Schema coverage is 100%, so the parameter forum_id is well-documented. The description reinforces that forum_id equals the paper note id, adding slight clarification. Baseline is 3, and the description provides marginal additional 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 that the tool retrieves a paper and all its child notes (reviews, rebuttal, decision, metareview). The verb 'get' and resource 'paper' are specific, and it distinguishes from sibling tools like get_note which retrieves a single note.

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

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

The description implies usage when you need a paper with its child notes but does not explicitly state when not to use it or mention alternatives like get_note for single notes. With a sibling get_note, more explicit guidance would improve this 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds no further behavioral context beyond what is in 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 concise sentence, front-loaded with the key information. It is efficient but may be slightly too terse.

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 read-only operation, the presence of an output schema, and the annotations covering safety and idempotency, the description provides adequate context for selection and invocation.

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

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

Schema coverage is 100% and the description echoes 'by group id' which matches the parameter. No additional semantic value beyond the schema's description of group_id.

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 'Venue (group) metadata' using a group id. The verb 'get' and resource 'metadata' are specific, and it distinguishes from the sibling 'list_venues' which lists all venues.

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 group id') but does not provide explicit when-to-use or when-not-to-use guidance, nor alternatives. Usage is inferred but not stated.

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

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds no behavioral details beyond the annotations, such as pagination behavior, sorting, or what happens with invalid venue_id.

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 (one sentence) and front-loaded with the core purpose. It efficiently states the main action and required input, though it could benefit from slightly more detail without becoming verbose.

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

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

Given the tool has multiple parameters (sort, limit, offset) and an output schema, the description is incomplete. It omits any guidance on using pagination or sorting, and does not clarify what the output contains, leaving the agent with insufficient context beyond the schema.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds minimal extra meaning by mentioning venue_id but does not elaborate on sort, limit, or offset parameters, which are already well-described in the schema.

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

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

The description clearly identifies the resource (papers submitted to a venue) and implies listing, but uses a noun phrase instead of a verb, making it slightly less direct. It distinguishes from sibling tools like get_venue or get_paper by specifying submissions to a venue.

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 only instructs to pass the venue group id, without explaining when to use this tool over alternatives like search_notes or search_within for finding submissions. No context on appropriate scenarios or exclusions is provided.

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

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

Annotations already indicate read-only and idempotent. Description adds value by listing returned fields and default behavior (active only). No contradictions.

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

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

Two sentences, no redundancy. Every word adds value.

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

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

Sufficient for a simple list tool. Includes return fields and usage context. Could mention pagination but not necessary.

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 the single parameter with description. The description implies default excludes inactive but does not repeat parameter details. Baseline score since schema coverage is 100%.

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 'List the caller's active subscriptions' - specific verb and resource. Distinguishes from sibling tools like 'subscribe' and 'unsubscribe'.

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: 'Use this to review what you're monitoring before adding more or to find an id to cancel.' Suggests when to use but does not explicitly exclude alternatives.

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

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

Annotations already declare safe read-only, idempotent, and non-destructive behavior. The description adds only the resource type (conferences/workshops), providing minimal additional behavioral context 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 just two sentences, front-loads the action and resource, and every sentence adds value with no wasted words.

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

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

Given the presence of an output schema and complete parameter documentation, the description adequately covers the tool's purpose and usage. It could mention the filtering capability but the schema covers that.

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

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

Schema description coverage is 100%, so the schema fully documents parameters. The description does not add extra meaning about the parameters, meeting the baseline for high 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 verb 'List' and resource 'venue groups (conferences, workshops)', and distinguishes from siblings like 'get_venue' and 'list_submissions' by specifying the scope and use case.

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 advises using the returned group id to query submissions, implying the tool's purpose for obtaining ids. However, it does not explicitly state when not to use it or list alternatives, which would improve guidance.

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

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

Annotations indicate non-readOnly and non-destructive. The description adds that it's rate-limited (5 per day), free, doesn't count against quota, and that team reads digests daily with roadmap impact. This provides useful 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?

Three sentences: first states purpose, second gives usage guidelines, third adds constraints and context. No wasted words, front-loaded with essential 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?

Covers all necessary aspects: when to use, what to include, constraints, and post-submission handling. Despite no output schema, the description explains impact (digests, roadmap). Complete for a feedback tool.

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

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

Schema coverage is 100% with detailed descriptions, but the description complements by reinforcing categories, advising to describe issues in terms of Pipeworx tools/packs, and giving message length guidelines. Adds meaning beyond schema.

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

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

The description clearly states it is for sending feedback to Pipeworx team, with specific categories (bug, feature, data_gap, praise). This distinctively sets it apart from all sibling tools which are for information retrieval or actions, not feedback.

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 (bug, feature/data_gap, praise) and what not to do (don't paste end-user prompt). Also mentions rate-limit and free usage, guiding appropriate use.

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

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

Annotations already cover read-only, idempotent, non-destructive. Description adds data source (CF analytics-engine), privacy (no PII), caching behavior (5min-1h). No contradictions.

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

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

Three efficient sentences: purpose, use cases, technical context. Front-loaded, 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?

For a simple tool with one optional param and no output schema, description fully covers return value, usage, and technical details. No 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 100%, but description adds semantic guidance: 'Shorter windows surface what's hot right now; longer windows show steady-state demand.' This enhances the enum 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?

Clearly states it returns top tools, packs, and call volume over a window (24h, 7d, 30d). The verb 'Returns' with specific resource distinguishes it from sibling tools like 'discover_tools'.

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

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

Lists three concrete use cases (discovering hot data, confirming canonical tool, aligning use case). Implicitly contrasts window choices but lacks explicit 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?

Annotations indicate read-only, idempotent, and non-destructive. Description adds substantial behavioral context: semantic anchor (Jaccard similarity ≥0.30), partition filter (dropping placeholder slugs), fill check against CLOB depth with realizable edge calculation. These details exceed what annotations provide and help the agent understand internal logic and limitations.

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 clear sections: requirement, mode explanations, semantic anchor, partition filter, response format, fill check. Despite length, every sentence adds value and the critical requirement is front-loaded. 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?

Despite no output schema, the description fully explains the response structure (opportunities array with fields, partition_check object) and the fill check logic. It covers all major aspects needed for correct agent invocation: required parameters, internal checks, response format, and reference to sibling tool for additional functionality.

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 decent descriptions for both parameters. The description adds further meaning: explains that event walks child markets and performs partition checks, while topic searches related events and runs comparator across unions. This goes beyond the schema but the schema already provides sufficient clarity, hence above baseline but not maximum.

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 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks'. It specifies two modes (event and topic) and distinguishes them from each other. It is distinct from sibling tools like polymarket_edges and polymarket_fill_risk, which focus on edges and fill risk respectively.

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 'REQUIRES one of `event` or `topic` — call with no args fails'. Recommends event for specific markets and topic for cross-event scanning, explaining what cross-event catches that single-event misses. Also guides to use polymarket_fill_risk for custom sizing, an explicit alternative.

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, openWorldHint, etc., and the description adds significant behavioral details: caching at KV level keyed on knobs, 1-hour cache, response including diagnostics for empty segments, and limitations of Fed bet data. 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 long but well-structured, front-loaded with a summary and then breaking down model families and response structure. Every sentence adds value, though it could be slightly more concise. Still, it's efficient for the 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?

For a tool with 9 parameters, no output schema, and complex nested response, the description is remarkably complete. It explains why segments might be empty, the Fed bet handling, caching behavior, and diagnostics. All relevant aspects are covered.

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

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

Schema coverage is 100%, so baseline is 3. The description adds context for parameters like slippage_pp (explaining Polymarket zero fees but typical bid/ask spread) and min_partition_leg_kelly (why min_kelly doesn't apply to partitions). This adds meaningful value 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 explicitly states the tool scans top Polymarket markets and returns opportunities where Pipeworx data disagrees with market price. It's built for 'what should I bet on today' and distinguishes from siblings by focusing on edge detection rather than arbitrage or risk analysis.

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 for use (discovering opportunities without paging) and explains tradeable-edge knobs. However, it lacks explicit when-not-to-use guidance compared to siblings like polymarket_arbitrage or polymarket_fill_risk. The exclusion of Fed bets from ranking is noted, but alternatives are not directly compared.

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, openWorldHint, idempotentHint, destructiveHint=false. The description adds significant behavioral detail: response structure (tracked, expired, snapshot_dates), decay computation on absolute value, snapshot gaps due to cache misses, and history limits (60-day TTL). 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 dense but well-structured, front-loading purpose and then detailing response sections and limits. While longer than ideal, every sentence adds value. Could be slightly more concise with bullet points, but is acceptable for a complex tool.

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

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

Given the tool's complexity (time-series telemetry, multiple response arrays) and lack of output schema, the description comprehensively explains all response fields, computation details, and limitations. It covers use cases, behavior, and edge cases (snapshot gaps, history bound).

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 both parameters with descriptions (100% coverage). The description adds defaults and max value for days, and explains window as snapshot family. However, it mostly reiterates schema info. No output schema exists, but description compensates with response details.

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

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

The description clearly states the tool's purpose: edge persistence and decay telemetry from daily snapshots. It answers a specific question about edge longevity and distinguishes itself from sibling tools like polymarket_edges (current edges) by focusing on historical trends.

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 for when to use the tool (to assess edge persistence/decay) and contrasts fresh vs. aged edges. While it doesn't explicitly state when not to use it, the distinction from siblings is clear. Guidance could be more explicit about alternatives.

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

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

Annotations (readOnlyHint, idempotentHint) are consistent and description adds behavioral details like 'walks the ladder and returns...verdict (clean|degraded|cannot_fill)' and warnings about stranded positions. 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?

Well-structured: begins with core purpose, then explains each mode with bold headers, and concludes with usage guidance. Slightly verbose but every sentence adds value; front-loaded with key 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?

Despite no output schema, description comprehensively lists all return fields for both modes, covers edge cases (thin_legs, forced_directional_risk), and explains critical risks. Completes the picture for effective tool use.

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

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

Schema coverage is 100%, and description enriches each parameter. For example, explains that in basket mode 'side' auto-detects based on partition sum, and 'size_usd' is settlement notional for baskets. Goes beyond schema 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?

Clearly states the tool's function: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' Distinguishes between single-market and basket modes with detailed explanations, and the purpose differentiates it from sibling tools like polymarket_arbitrage and 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 states when to use: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' Provides rationale about thin books and partial fills creating directional risk, offering clear alternatives and context.

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

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

Annotations already indicate read-only, open-world, and idempotent behavior. The description goes beyond by detailing safety fields (compatibility_warning, temporal_alignment, skipped_cross_type) and explaining edge cases where spreads are meaningless (aligned:false, or shape mismatches). 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 lengthy but well-structured: it starts with core purpose, then explains modes, response structure, and safety fields in a logical order. Every sentence adds value, though some detail might be condensed. Still, it earns a 4 for efficiency given the 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 output schema, the description fully explains the response structure (leg-by-leg prices, top_spreads_pp, compatibility_warning, temporal_alignment, counters). It covers the three parameters, their usage, and edge cases, making the tool self-contained for an agent to use correctly.

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

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

All three parameters have descriptions in the schema (100% coverage), so baseline is 3. The description adds value by explaining the two modes, enumerating the topic shortcuts, and clarifying that explicit tickers override the topic-mapped side. This justifies a score of 4.

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

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

The description clearly identifies the tool as computing cross-venue spread between Polymarket and Kalshi for the same question, specifying two distinct modes (topic shortcuts and explicit tickers). This is a specific verb+resource combination that differentiates it from sibling tools like polymarket_arbitrage or bet_research.

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 each mode (topic for pre-mapped shortcuts, explicit for custom pairings) and warns that most pre-mapped topics currently return compatibility_warning, guiding the agent not to assume tradeability. It also explains when spreads are safe to use (aligned:true).

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, idempotentHint=true, destructiveHint=false. Description adds value by explaining scoping to identifier and the dual behavior (retrieve vs list). No contradictions.

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

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

Three sentences, each essential: purpose, usage examples, scoping and pairing. Front-loaded with main action, no wasted words.

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

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

Given the tool's simplicity (one optional parameter, no output schema), the description fully covers purpose, usage, parameter semantics, and behavioral context. No 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% with a brief description of 'key'. Description adds meaning: explains that omitting key lists all keys, and provides concrete use case examples.

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

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

The description uses specific verb+resource ('Retrieve a value... via remember, or list all saved keys'), clearly distinguishing from siblings like remember and forget by naming them.

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

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

Explicitly states when to use (look up context stored earlier) and when to omit key (list all). Also mentions pairing with remember and forget for full 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 declare readOnlyHint=true and destructiveHint=false. Description adds behavioral context: mark_read flag mutates read state (non-destructive, idempotent) and mentions polling suitability. 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?

Four sentences, front-loaded with main action, no wasted words. Each sentence adds unique information (purpose, return fields, filtering, mark_read behavior, alternative access).

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, description covers return fields (source, citation_uri, raw event payload), all optional parameters, and usage scenarios (polling, alternative endpoint). Addresses tool complexity fully.

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% description coverage, providing baseline 3. Description adds value by explaining the mark_read parameter's side effect (flagging events read) and giving a concrete type example ('sec_8k'), enhancing understanding beyond schema.

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

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

The description starts with 'Pull fired events from your subscription feed', specifying the verb (pull), resource (fired events from feed), and distinguishing it from sibling tools like list_submissions or list_subscriptions by focusing on alert events.

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 (filter by type/since, mark_read for read tracking, polls work fine) and provides alternative access method (GET registry.pipeworx.io/alerts.json for scripts/dashboards), guiding optimal tool 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 mark the tool as readOnly, idempotent, and non-destructive. The description adds substantial behavioral context: the tool fans out to multiple sources in parallel, explains fallback behavior, mentions rate-limiting triggers, and states the USPTO failure mode. It describes the return structure (changes grouped by source, total_changes, 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 a single dense paragraph, but every sentence contributes meaningful information. It is front-loaded with example user queries. Minor deduction for density; breaking into bullet points could improve scannability, but current structure is efficient and complete.

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 clearly states what the tool returns: structured changes grouped by source, total_changes count, and pipeworx:// citation URIs. It covers the multi-source behavior, fallback logic, and parameter nuances. For a complex tool with three parameters and no output schema, this description is remarkably complete.

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

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

Schema coverage is 100%, so each parameter has a description in the schema. However, the tool description adds significant value beyond the schema: it explains the 'since' parameter accepts both ISO dates and relative shorthand with examples ('7d', '3m'), and the 'value' parameter accepts tickers or CIK numbers. This enriches the semantic understanding beyond the schema's basic 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 begins with clear user-facing queries ('What's new with X') and explicitly states it is a change feed for a company over a recent window. It differentiates from sibling tool entity_profile by stating when to use the alternative. The verb 'fans out' combined with the listed sources makes the scope 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 provides explicit when-to-use guidance with natural language examples. It directs users to entity_profile for static profiles, establishing a clear exclusion. It also explains the fallback chain from GDELT to GNews due to rate limits, and notes the USPTO soft-fail. Parameter format guidance is given for 'since'.

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 non-destructive write (readOnlyHint false, destructiveHint false, idempotent true). Description adds scope: 'scoped by your identifier', persistence details: 'authenticated users get persistent memory; anonymous sessions 24 hours'. 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?

Three sentences, each purposeful: first states core purpose, second gives usage context, third adds behavioral details. No wasted words.

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

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

For a simple write tool with no output schema, description covers purpose, usage, behavior, and pairing. Annotations provide safety info. Complete for the complexity.

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

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

Schema coverage is 100% with clear descriptions for key and value. Description adds no new semantics beyond examples (resolved ticker, etc.), but baseline 3 is appropriate given schema richness.

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 saves data for reuse, with examples like 'resolved ticker, target address, user preference'. It distinguishes from siblings 'recall' 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 explicitly says 'Use when you discover something worth carrying forward' and pairs with recall and forget. It doesn't explicitly state when not to use, but provides strong contextual guidance.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds that each call cascades through several internal lookup endpoints, replacing 2-3 manual lookups, and auto-disambiguates company names. No contradictions.

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

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

The description is concise (~150 words), front-loaded with examples and use case, and every sentence conveys essential information without redundancy.

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

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

Covers purpose, input formats, output details (ticker, CIK, company name; RxCUI, ingredient, brand), and internal cascading. No output schema, but return values are described. Mentions citation URIs. Could benefit from explicit output structure or error handling notes.

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%. The description elaborates on parameter meanings for each type (company accepts ticker, CIK, or name; drug accepts brand or generic) and provides examples ('AAPL', 'ozempic'), adding significant value over the schema alone.

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 resolves names to canonical identifiers, provides example queries, and lists supported entity types (company, drug) with specific return values. It distinguishes from sibling tools by positioning as a preliminary lookup step.

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

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

Explicitly says 'Use FIRST whenever you have a name but need an ID,' providing clear usage context. Does not explicitly state when not to use, but the guidance is strong and no alternative tools are named.

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 the tool as read-only, idempotent, and non-destructive. The description adds value by explaining the internal probing mechanism, ranking logic, and output format (score, confidence, signal density). It also notes that the first entity is treated as the subject, which is a behavioral detail not in annotations.

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

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

Three sentences that are front-loaded with the core purpose, followed by process and use case. Every sentence earns its place—no redundancy or filler.

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

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

The tool has no output schema, but the description briefly explains what the ranked list contains (score, confidence, signal density). Combined with annotations (readOnlyHint, openWorldHint), it provides sufficient understanding. Could mention edge cases or limitations, but overall adequate.

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

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

Schema description coverage is 100%, so the description does not need to add parameter details. The main description does not elaborate on parameters beyond what the schema already provides, meeting the baseline but adding no 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?

Clearly states that the tool compares AI visibility across multiple entities, uses ai_visibility_check internally, and returns a ranked list with scores. Differentiates from sibling 'ai_visibility_check' (single entity) and other comparison tools like '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?

Explicitly gives a use case (competitive AI-marketing audit) and implies that for a single entity one should use ai_visibility_check. However, it does not explicitly state 'when not to use' or list 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?

Beyond annotations (readOnly, idempotent, openWorld), description adds critical behavioral details: partial failures degrade gracefully, bundlephobia first measurement may take 5-30s, sources_failed lists timeouts. No contradiction with annotations.

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

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

Single dense paragraph front-loads the main purpose, lists use cases, return fields, ecosystem notes, and failure behavior. 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?

Despite no output schema, the description completely details the return value (summary block fields, per-advisory detail, links, alternative versions) and covers edge cases (partial failures, timeouts). It also specifies ecosystem limitations.

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 both parameters with descriptions (100% coverage). Description adds the ecosystem constraint ('NPM ecosystem only in v1') which is helpful for the package parameter, but otherwise does not add significantly beyond schema.

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

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

The description clearly states the tool is a composite check for deciding whether to add an npm package, listing specific sources (deps.dev, bundlephobia) and return fields. It distinguishes from sibling tools which are for other domains like AI visibility, betting, notes.

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 (agent asks 'is X safe/popular/small' or 'what does adding lodash cost me') and provides alternatives: 'PyPI / Maven / Cargo / Go fall under deps.dev:version directly.'

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, idempotentHint, destructiveHint false, and openWorldHint. The description adds behavioral context beyond annotations by specifying the return format (note ids, titles, venues) and optional filters (content_field, signature). It does not contradict annotations.

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

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

The description is a single, well-structured sentence that front-loads the core action, then adds optional modifiers, and ends with the output. No wasted words; every phrase adds information.

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

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

Given the tool's complexity (5 params, output schema exists, annotations present), the description covers the main purpose, optional restrictions, and return values. It lacks details on ranking or pagination but these are covered by parameters. Sufficiently complete for effective use.

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

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

Schema description coverage is 100%, so the schema already documents all parameters. The description adds marginal semantic value by grouping parameters into categories (restrict, filter) and giving examples (e.g., 'title', 'abstract') but does not substantially improve understanding beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly identifies the tool's core function: full-text search of OpenReview notes (papers, reviews, decisions). It specifies the resource ('notes') and the action ('search'), and distinguishes it from sibling tools like 'search_within' or 'deep_research' by naming the specific domain (OpenReview) and 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 implies when to use (search OpenReview notes) but does not explicitly state when not to use or mention alternatives. It provides no guidance on choosing between this and other search tools like 'search_within' or 'deep_research'. A score of 3 reflects the lack of explicit usage boundaries.

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 substantial behavioral details beyond annotations: chunking strategy (500-char overlapping windows), embedding model (BGE-base-en), similarity (cosine), size cap (200K chars with truncation flag), and output format (passages with offsets and similarity scores). 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?

Concise three-sentence structure with front-loaded purpose and key details. Every sentence adds critical information; no fluff.

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

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

Despite no output schema, description fully compensates by describing output fields (passages, offsets, similarity scores). Also covers input constraints, chunking, embedding, and truncation—complete for a retrieval tool.

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

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

Schema coverage is 100%, and description adds value by clarifying query as natural-language with examples, specifying truncation behavior for text, and implying limit defaults. Enhances understanding beyond schema alone.

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 'Semantic search INSIDE a fetched record,' with specific verb and resource. Distinguishes from siblings by describing pairing with ask_pipeworx_grounded and contrasting with full-document search.

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 explains when to use: when the record is too big for the prompt, to save context. Mentions alternative use case with ask_pipeworx_grounded, providing clear guidance on tool 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?

The description adds significant behavioral context beyond annotations: availability of delivery channels, SMS rate limit (10/day), phone verification requirement, webhook auto-disable after 10 failures, and one-time signing secret. It is consistent with annotations (readOnlyHint=false, destructiveHint=false) and does not contradict them.

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

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

The description is thorough yet well-structured, with clear sections for types and delivery channels. It front-loads the core purpose. While slightly lengthy, every sentence provides valuable information without redundancy.

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

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

Given the complexity (3 parameters, nested objects, multiple subscription types), the description covers all necessary details: required parameters, type-specific filters, delivery options with important caveats, and return value. No output schema is provided, but the description adequately explains what is returned (subscription id, webhook secret).

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?

Even though schema coverage is 100%, the description enriches each parameter with concrete examples and usage details (e.g., sec_8k items codes, polymarket_edge topic, delivery constraints). This adds substantial meaning beyond the schema itself.

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 ('Create a proactive monitoring subscription') and the resource ('live-data event stream'). It specifies the return value ('Returns the new subscription id') and lists supported types, distinguishing it from sibling tools like list_subscriptions and unsubscribe.

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?

It explicitly requires a Pipeworx OAuth account and states that anonymous and BYO accounts cannot persist subscriptions. It provides context for when to use (proactive monitoring) and lists types with examples, though it does not explicitly mention when not to use or compare with all 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?

Annotations already declare readOnly, idempotent, openWorld, non-destructive. Description adds that it returns example questions with tool shapes from live catalog, adding context beyond annotations. 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?

Description is detailed but efficient, front-loaded with user questions, then output explanation, then usage guidance. A bit wordy 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 no output schema, the description thoroughly explains what is returned (category-bucketed examples with tool calls). Covers all aspects expected for an onboarding tool.

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

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

Schema coverage is 100% with description for topic. Description adds value by listing example values and saying 'omit for cross-category spread', enhancing understanding beyond schema.

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

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

Description clearly states it returns category-bucketed example questions with exact tool/argument shapes. Verb is implied ('suggest') but the action and resource are unambiguous. Distinguishes from siblings as onboarding entry point.

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

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

Explicitly says 'Use this FIRST' when unsure what Pipeworx can do. Explains topic parameter to focus. Provides context for when to use vs. other 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.

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

Adds beyond annotations: explains deactivation (not deletion) ensures historical events remain, and ownership enforcement. Annotations provide idempotentHint=true and destructiveHint=false, but description clarifies the real-world effect.

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 no wasted words. Action first, then constraints, then side effects. Front-loaded and 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?

Completely describes a simple 1-parameter tool with no output schema. Covers ownership, mutation type, and side effects on history.

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

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

Schema coverage is 100% with a clear description of the id parameter. Description adds that id is returned by subscribe, but that's already in schema. Baseline 3 applies.

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

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

Description clearly states the verb 'cancel a subscription by id' and distinguishes from siblings like subscribe and list_subscriptions by specifying ownership enforcement and the deactivation behavior.

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 context: only own subscriptions, deactivation not deletion. Implicitly tells when to use (cancelling) but doesn't explicitly exclude 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?

Annotations already indicate read-only, open-world, idempotent, and non-destructive behavior. Description adds specific return values (verdict types, structured form, citation, percent delta) and explains how it works (NL parsing → entity resolution → data lookup → numeric comparison), enhancing transparency without contradicting 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 fairly concise given the complexity, front-loading key purpose and usage. Could be slightly tighter but remains effective without redundant sentences.

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

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

No output schema exists, but the description fully explains return types and structure. It also covers limitations (v1 scope) and the tool's efficiency advantage. Complete for an agent to understand usage and expectations.

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

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

Only one parameter 'claim' with 100% schema description coverage. The description provides examples of proper claim formatting, adding modest value beyond the schema's own description.

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

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

The description explicitly states the tool verifies natural-language claims against authoritative sources, with specific examples (e.g., "Is it true that…") and scope (company-financial claims via SEC EDGAR + XBRL). It clearly distinguishes from sibling tools by noting it replaces multiple sequential calls.

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

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

Directly says 'Use whenever the agent needs to check whether something a user said is factually correct.' Also provides scope limitations ('v1 supports company-financial claims...'), giving clear when-to-use and constraints.

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