Sciencebase

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

Annotations already indicate read-only and idempotent behavior. The description adds transparency about external calls: default model is free, probing Anthropic requires a BYO API key with direct payment. This addresses cost-related behavioral traits 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 very concise: three sentences covering action, output, and use cases. Every sentence is informative and essential. No redundant words or phrases.

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

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

The description covers all key aspects: parameters (via schema), return format (per-model and combined view), and use cases. It lacks explicit error handling or rate limit details, but given the tool's simplicity, it is nearly 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 baseline is 3. The description adds value by specifying allowed model values ('workers-ai', 'anthropic'), explaining the API key format and usage, and providing examples for the context parameter. This goes beyond the schema's simple 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 uses specific verbs ('probe', 'score') and resources ('LLMs', 'visibility'). It clearly states the tool checks AI awareness of an entity across multiple models, distinguishing it from sibling tools like 'ask_pipeworx' or 'deep_research' which have different purposes.

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 outlines use cases ('AI-marketing audits, pre-launch brand checks, competitive monitoring') and explains when to use the optional API key. It provides clear context but does not explicitly state when not to use the tool or compare with 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 provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description adds that it returns structured answers with stable pipeworx:// citation URIs, and explains the routing mechanism to 3,745 tools across 884 sources. 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 front-loaded with the key preference statement and uses bullet-style examples. It is somewhat long but every sentence adds information. Could be slightly more concise without losing content, but structure is effective.

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

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

Given the complexity (3,745 tools, 884 sources) and lack of output schema, the description adequately explains what the tool does, what to expect (structured answer with citations), and provides extensive examples. It covers the required information for an agent to use it correctly.

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

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

Schema coverage is 100% with all 6 parameters described (one required parameter 'question' plus 5 aliases). The description adds value by providing example questions that illustrate how to use the parameter, but the schema itself already documents the aliases and descriptions. Examples are helpful for usage, justifying a 4.

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

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

The description clearly states the tool routes natural language queries to authoritative structured data sources with citations. It distinguishes itself from web search by specifying preference, and the verb 'ask' combined with resource 'Pipeworx' is specific. Sibling tools like 'ask_pipeworx_grounded' exist but the description does not differentiate from them, though the purpose is still clear.

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

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

Explicitly states 'PREFER OVER WEB SEARCH' and provides a comprehensive list of domains and example queries. It tells when to use the tool (factual questions about real-world entities, events, numbers) with specific triggers like 'what is', 'look up', etc. Does not mention when not to use, but positive guidance is strong.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds behavioral details: costs an extra LLM call, returns structured success/refusal format with specific refusal reasons, and that it uses only the tool result. 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 two sentences, dense with information: routing, behavior, return format, use cases. It is well-structured and front-loaded. Slightly verbose due to example refusal reasons, but still concise.

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

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

Despite no output schema, the description fully specifies the return structure: {answer, evidence, confidence, source, fetched_at, refusal_reason:null} and lists all refusal reason enums. It also explains the mechanism and use cases, making it complete for high-stakes queries.

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% with 6 parameters (question and 5 aliases). The description mentions that it accepts natural language but does not add meaning beyond what the schema already provides. Baseline 3.

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

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

The description clearly states the tool as a 'hallucination-resistant answer mode for high-stakes reads' and distinguishes it from ask_pipeworx by explaining it extracts answers only from tool results and returns explicit refusals. It uses specific verbs and unique selling points.

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: 'whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' and when not to: 'prefer ask_pipeworx for casual lookups'. Provides clear decision 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 declare readOnlyHint, openWorldHint, idempotentHint. Description adds extensive behavioral details: fan-out patterns, resolver contract with confidence levels, parent_event extractor, news fallback fields, safety low-confidence short-circuit, wide-spread handling, and resolution-rule risk. 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 lengthy (several paragraphs) but front-loaded with core purpose. However, it contains many details that could be tightened, and later sections are dense. Still, every sentence contributes to understanding.

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 thoroughly explains response shapes (market, analysis, evidence), resolver contract, parent_event, news fields, safety mechanisms, and resolution-rule risk. It covers edge cases and provides sufficient context for an agent to use the tool effectively.

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

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

Schema coverage is 100% (all parameters described). Description adds meaning: market parameter explains slug/URL/question text, depth explains quick vs thorough, include_raw explains summarization vs full payloads. Slightly redundant with schema but adds 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 explicitly states it researches a Polymarket bet by pulling Pipeworx data, accepts slug/URL/question text, resolves, classifies, fans out, and returns evidence. It clearly distinguishes from siblings like polymarket_arbitrage by focusing on a single 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 provides explicit use cases: 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z"'. It gives category-specific fan-out examples but lacks explicit exclusion cases, though context implies 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?

Description adds rich behavioral detail beyond annotations: specifies data sources (SEC EDGAR/XBRL for companies, FAERS for drugs), handles fiscal year variations, sorts results by primary metric, and returns 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?

Description is fairly long but well-structured with a clear progression: example queries, usage guidance, type-specific details, and output format. Every sentence adds value, though could be slightly more 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?

No output schema, but description adequately covers what the tool returns ('paired data + pipeworx:// citation URIs'). For a tool with two entity types and simple parameters, this is sufficient. Could mention ordering by metric more explicitly.

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 both parameters described, but the description adds significant context: explains what data is pulled for each type, the format of values (tickers vs drug names), and count limits. Slightly above baseline due to added clarity on behavior.

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 tool does 'side-by-side comparison of 2–5 companies or drugs' using specific verbs like 'compare', 'rank', 'head to head'. It differentiates from siblings by explicitly preferring over sequential lookups and distinguishing between entity types with distinct data sources.

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

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

Explicitly says 'ALWAYS PREFER over sequential single-pack lookups when comparing entities', providing clear guidance on when to use this tool. Also gives example queries and explains the efficiency gain, leaving no ambiguity.

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 only indicate read-only, open-world, idempotent. Description adds details: parallel decomposition, verbatim evidence with citations, explicit gaps[], never invents, expected time 15-60s. All 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?

Packed with useful information, every sentence earns its place. Front-loaded with main purpose, followed by process, output format, usage guidance, and constraints. 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?

Comprehensive for a complex tool: covers input, behavior, output format (findings packet with evidence, gaps), time expectation, account requirements, and comparison with sibling. No output schema, but description covers it well.

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

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

Schema coverage is 100% with descriptions. Description adds default and paid plan info for depth param, and clarifies that broad questions are fine for question. Adds value but not essential.

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 'Grounded multi-source research in ONE call' and describes decomposition, routing, and extraction. Distinguishes from sibling ask_pipeworx by noting it's for single lookups.

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 for broad or multi-part questions' and contrasts with ask_pipeworx for single lookups. Also mentions account requirement and paid plan for thorough depth.

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 useful behavioral context: returns top-N relevant tools with full input schemas and curated examples, each result ready to call directly. 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 slightly long but dense with information. It is front-loaded with the main purpose and structured logically. Every sentence adds value, though minor trimming could improve conciseness.

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

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

Given no output schema, the description adequately explains the return format (names, descriptions, schemas with examples). For a discovery tool with 6 parameters, this is sufficient to understand behavior and 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%, so baseline 3. The description adds value by listing multiple aliases for the query parameter and providing concrete examples. This helps agents understand acceptable inputs beyond the schema.

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

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

The description clearly states that the tool finds tools by describing a data or task, listing many specific domains. It distinguishes itself from siblings as a discovery tool that returns top-N relevant tools with complete information, ready to call.

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 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' It provides clear context for when to use, though it does not explicitly state when not to use or mention 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 readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. Description adds critical behavioral context: USPTO API sunset soft-fail, GDELT→GNews fallback, and specific return fields. 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 front-loaded with example queries and is thorough, but slightly lengthy. Every sentence earns its place, though could be trimmed slightly without losing 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?

Despite no output schema, description lists all returned data fields (cik, filings with URIs, fundamentals, patents, news, LEI) and highlights limitations (USPTO sunset). Complete for a complex multi-source 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 both parameters described. Description adds meaning by explaining value accepts ticker or zero-padded CIK (not names), and type enum is currently limited to 'company'. 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?

Description clearly states 'full cross-source profile of a US public company in ONE parallel call'. It specifies the verb 'profile' and resource 'entity', and distinguishes from siblings like resolve_entity and compare_entities by explicitly noting name resolution is not supported.

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 SEC/XBRL/news lookups' for holistic views, and advises to use resolve_entity first if only a name is available. Provides clear when-to-use and 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 provide destructiveHint=true and idempotentHint=true, so the agent knows it's destructive and safe to repeat. The description adds that it deletes a memory by key and mentions clearing sensitive data, but does not elaborate on effects of deleting a nonexistent key or authorization needs. It adds some context but not rich behavioral details 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 two sentences: first sentence defines purpose, second gives usage guidance. Every sentence earns its place with no wasted words. Front-loaded with the 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?

For a simple one-parameter tool with no output schema, the description is complete. It covers purpose, when to use, and sibling tools. No additional information is needed.

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

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

Schema coverage is 100% and the parameter description 'Memory key to delete' is clear. The description's mention of 'by key' adds no new semantic detail beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states 'Delete a previously stored memory by key.' It uses a specific verb ('delete') and resource ('memory'), identifying the key as identifier. It explicitly mentions pairing with siblings 'remember' and 'recall', distinguishing it from other tools.

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

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

The description provides explicit use cases: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also suggests pairing with siblings, offering clear context. It does not explicitly state when not to use, but the given scenarios are sufficient.

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

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

Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint) already indicate safe, non-destructive operation. The description adds behavioral context: fetches the page, extracts title/description/key links, emits standard llms.txt markdown. However, it doesn't disclose potential risks like external fetch failures or rate limits, which would be helpful.

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: two sentences plus a bullet list of use cases. It front-loads the core purpose, then adds context. Every sentence is informative without redundancy. Ideal length for clarity and efficiency.

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 (2 parameters, no output schema), the description covers input, behavior, output format, and use cases. It fully explains what the tool does and how to use it. No gaps remain.

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% (both parameters documented). The description adds minimal value beyond the schema—'Fetches the page' implies url is a site URL, but no new format or constraints. Baseline 3 is appropriate since the schema already covers parameter 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 identifies the tool's purpose: generating a production-ready llms.txt file for any URL for AI crawlers. It specifies the verb (generate), resource (llms.txt file), and context (site indexing). This is distinct from sibling tools like scan_competitor_ai_presence, which focuses on auditing AI presence rather than generating a file.

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 lists concrete use cases: getting a client's site indexed, drafting for your own project, or auditing a competitor. It provides context on when to use, but does not explicitly state when not to use or mention alternatives. The absence of exclusions keeps it clear but slightly less directive.

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 readOnly, openWorld, idempotent, and non-destructive behavior. The description adds 'Keyless' (no authentication required) and details the return content, exceeding the burden. 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 plus an example, no wasted words. The most critical information (what it does, what it returns, an example) is front-loaded.

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

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

Despite no output schema, the description covers the main return fields and behavior. It lacks mention of error handling or what happens if the id is invalid, but for a simple get operation it is 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?

With 100% schema coverage, the single parameter 'id' is well-documented in the schema. The description adds value by providing an example value and clarifying 'Keyless' context, which is helpful but not essential.

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

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

The description clearly states it retrieves a single ScienceBase catalog item by id, lists the returned fields (summary, categories, types, dates, contacts, web links, attached files), and provides an example id. This distinguishes it from sibling tools like search_items and item_children.

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 for fetching a specific known item by id but does not explicitly state when not to use it (e.g., for searching) or compare to alternatives. The sibling list suggests alternatives, but direct guidance is missing.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds 'Keyless' (no authentication required) and explains the hierarchical behavior. 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 extremely concise: two sentences with no fluff. The primary purpose is front-loaded, and every sentence adds value.

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

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

Given the tool's simplicity (list children with optional pagination) and the absence of an output schema, the description adequately covers what the tool does and how to use it. It lacks details on return format but is sufficient for agent selection.

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

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

The input schema has 100% description coverage for both parameters (limit, parent_id). The description does not add additional semantic meaning 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 explicitly states the action: 'List the child items of a ScienceBase catalog item.' It clearly identifies the verb (list), resource (child items), and context (ScienceBase catalog), and distinguishes from related tools like get_item and search_items.

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 notes the hierarchical nature and suggests using get_item to check has_children, providing clear usage context. It implies when to use this tool (after checking parent has children) 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 readOnlyHint=true and destructiveHint=false. Description adds list of returned fields but does not disclose additional behavioral traits beyond annotations.

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

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

Two efficient sentences: first states purpose and outputs, second gives usage guidance. 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 read-only list tool with one optional parameter, description covers returned fields and usage context completely. No output schema needed.

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

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

Schema coverage is 100% with parameter 'include_inactive' already described. Description does not add meaning beyond the schema.

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

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

Description clearly states verb 'List' and resource 'subscriptions' with caller scope. Distinguishes from siblings like subscribe and unsubscribe by listing returned fields.

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: 'review what you're monitoring before adding more or to find an id to cancel.' No exclusion criteria but context is clear.

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

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

Beyond annotations, the description discloses rate limits (5 per identifier per day), that it doesn't count against quota, and its non-destructive nature. This adds significant transparency for agent decision-making.

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

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

The description is front-loaded with the primary purpose and uses bullet-like structure for categories. It is slightly verbose but every sentence adds value.

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

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

Given the tool's simplicity (3 params, no output schema), the description is complete. It covers all parameter behaviors, rate limits, quota impact, and usage examples, leaving no critical gaps.

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

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

Schema coverage is 100% with descriptions. The description adds value by explaining the type enum in context and providing guidelines for message content (e.g., be specific, don't paste user prompts), enhancing the schema's explanations.

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: sending feedback to Pipeworx team. It enumerates specific use cases (bug, feature, data_gap, praise) and distinguishes itself from sibling tools by focusing on feedback rather than queries or actions.

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 for each feedback type and advises what to avoid (e.g., don't paste the end-user's prompt). It mentions rate limits and that it's free, but doesn't explicitly compare to 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, idempotent, non-destructive. Description adds caching details (5min-1h), aggregation source (CF analytics-engine), and privacy assurance (no PII), which go beyond annotations.

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

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

Description is extremely concise, front-loads the core function, and lists use cases in a bullet-like format. 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?

For a simple read-only tool with one parameter and no output schema, the description fully covers what the tool returns, caching behavior, and use cases. It is complete for an AI agent to select and invoke correctly.

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

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

Schema coverage is 100% with a clear description for the window parameter. The tool description adds context about short vs long windows, but this is essentially redundant with the schema description. 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 it returns top tools, top packs, and total call volume over selectable windows. It distinguishes from siblings like ask_pipeworx and discover_tools by focusing on aggregated popularity signal from other AI agents.

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?

Three explicit use cases are given: discovering hot data sources, confirming canonical tools, and aligning use cases with demand. However, no explicit exclusions or alternatives to sibling tools are mentioned.

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

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

Adds significant behavioral details beyond annotations: explains Jaccard similarity filter, partition filter, fill check, and that calling without args fails. Annotations indicate read-only, idempotent, non-destructive; description aligns and adds context but could be more structured.

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 and somewhat verbose; key information is front-loaded but there is redundancy (e.g., partition_check explained twice). Could benefit from more structured formatting (e.g., bullet points) to improve scanability.

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?

Comprehensively covers both modes, algorithmic details, edge cases (placeholders, similarity), and response structure. References sibling tools for further actions. No output schema exists, but description explains return format adequately.

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 with examples, accepted formats (URLs), and mode-specific behavior. Provides clear guidance on when to use each parameter.

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

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

The description clearly states the tool finds arbitrage opportunities via monotonicity violations and partition-sum checks, distinguishes two modes (event and topic), and provides specific examples. It contrasts with sibling tools like polymarket_edges and polymarket_fill_risk.

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 requires one of 'event' or 'topic', recommends event mode for specific markets, and explains topic mode for cross-event scanning. References sibling tools for custom sizing. However, lacks explicit 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?

Annotations indicate readOnlyHint, idempotentHint, and non-destructive behavior. The description adds extensive behavioral context: caching strategy, internal model families, diagnostic output, segment structure, and details on edge calculation and filters. 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 structured with clear sections and front-loaded purpose. While verbose, every sentence adds value for a complex tool. Minor redundancy could be trimmed, but overall appropriate for the tool's sophistication.

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

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

No output schema exists, so the description fully explains the return structure: by_segment with three groups, fed_candidates, and _diagnostics. It also covers edge fields, 24h move warning, and tradeable-edge knobs, ensuring the agent understands the complete response.

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

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

Schema coverage is 100%, but the description adds significant meaning beyond parameter names and types. It explains the distinction between min_kelly and min_partition_leg_kelly, the role of category_filter in selecting segments, and the rationale behind each param like slippage_pp and max_spread_pp.

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

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

The description clearly states the tool scans top Polymarket markets for opportunities where Pipeworx data disagrees with market price, with the explicit use case 'what should I bet on today.' It distinguishes itself from sibling tools like polymarket_arbitrage and polymarket_edge_tracker by focusing on daily discovery without paging hundreds of markets.

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 daily discovery, mentions caching (1h), and details adjustable knobs. It implies usage for initial opportunity scanning but does not explicitly state when to avoid this tool or suggest alternatives like polymarket_edge_tracker for tracking over time.

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 readOnly and non-destructive behavior. The description adds rich behavioral details: history bounded by 60-day TTL, snapshot gaps, decay computed from daily closes, and response structure (tracked, expired, snapshot_dates). 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 a single paragraph but effectively front-loaded with the core question. Every sentence contributes meaningful information, though it could be slightly more structured (e.g., separating response format). Not 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?

Without an output schema, the description fully explains the return values (tracked, expired, snapshot_dates) and their fields. It also covers limits and caveats (TTL, gaps), making the tool's behavior clear and 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 baseline is 3. The description adds value by explaining defaults (14 days, '1wk' window) and constraints (max 30 days) in context, plus linking parameters to the tool's functionality.

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: providing edge persistence and decay telemetry from daily polymarket_edges snapshots. It differentiates from siblings like polymarket_edges by focusing on trend analysis rather than raw snapshots.

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 (to understand edge longevity) and provides context with the example of fresh vs. old wide edges. It does not explicitly state when not to use or name alternatives, but the sibling list includes polymarket_edges, aiding inference.

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

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

Annotations indicate readOnlyHint, openWorldHint, idempotentHint are true. The description adds behavioral context: it is a risk check that walks the order book ladder, returns specific metrics (top_of_book, vwap_fill_price, slippage_pp, etc.), and warns about thin books and partial basket fills. 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 well-structured with sections (REQUIRES, SINGLE-MARKET, BASKET) and front-loads the core purpose. Each sentence adds value, though the length is justified by the tool's complexity. Slightly verbose but efficient for the information density.

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 the absence of an output schema, the description fully details return fields for both modes, covers edge cases (thin legs, forced directional risk), and provides usage restrictions. The tool is complex with two modes, and the description handles completeness well.

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

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

Schema coverage is 100%, but the description adds significant meaning beyond the schema: it explains parameter behavior in different modes (single-market vs basket) for side (default auto in basket) and size_usd (spend vs proceeds vs settlement notional), and adds constraints (clamp 10–1,000,000).

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: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It distinguishes two modes (single-market and basket) and explicitly contrasts with sibling tools like polymarket_arbitrage and polymarket_edges, stating when to use this tool instead.

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

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

The description provides explicit usage guidance: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It explains the rationale (theoretical overround not capturable, partial fills convert arb to directional position) and thereby tells the agent when and why to use this tool.

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

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

The description adds substantial behavioral context beyond annotations: it details safety fields (compatibility_warning, skipped_cross_type, temporal_alignment), explains the two modes, and warns that most pre-mapped topics yield compatibility warnings. There is 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, front-loading purpose then explaining modes, response, and safety fields. While every sentence adds value, slight trimming could improve conciseness.

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

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

Given the tool's complexity (cross-venue, two modes, multiple safety checks) and lack of output schema, the description covers purpose, parameters, usage, behavioral nuances, and response interpretation comprehensively.

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% with parameter descriptions. The description adds further value by explaining the interplay between topic and explicit parameters, and listing the 10 topic shortcuts. It provides context not present in 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 computes the cross-venue spread between Kalshi and Polymarket for the same resolving question. It specifies two modes (topic shortcuts and explicit pairings) and distinguishes itself from sibling tools like polymarket_arbitrage.

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

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

The description explains when to use (when bet shapes are equivalent) and when spreads are meaningless (compatibility warning, temporal misalignment). It does not explicitly mention when not to use over alternatives, but provides clear criteria for usage.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint. The description adds scope information and the behavior of listing all keys when omitting the key argument, providing extra 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 with clear structure, front-loading the action and purpose without any unnecessary words.

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

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

The description explains scope, pairing with siblings, and basic behavior. However, it does not describe the return format or error conditions, which is acceptable given no output schema but leaves some completeness gap.

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 describes the parameter. The description adds functional context by explicitly stating that omitting the key lists all keys, enhancing the schema's 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 uses the specific verb 'Retrieve' and noun 'value previously saved via remember' and 'list all saved keys', clearly distinguishing from siblings like remember and forget.

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

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

The description explicitly says when to use ('Use to look up context the agent stored earlier... without re-deriving it from scratch') and mentions scoping and pairing with remember/forget, but lacks an explicit 'when not to use' statement.

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

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

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint are true/false. The description adds valuable behavioral context: setting mark_read:true flags events as read to affect subsequent calls, and mentions polling behavior and alternative access. 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 four sentences, front-loaded with purpose and output, then filtering options, then operational guidance. Every sentence earns its place with no redundancy. Structure is logical 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?

Despite having no output schema, the description explains the return format (source, citation_uri, raw payload) and covers all parameters with their defaults. Annotations provide safety guarantees. The tool's behavior is fully specified 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?

Schema coverage is 100% with each parameter described. The description adds extra context beyond schema, such as the effect of mark_read on future calls and the default limit of 50, enriching the agent's understanding of parameter behavior.

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 pulls fired events from the subscription feed, specifies the returned data (source, citation_uri, raw payload), and mentions filtering options. It distinguishes itself by referencing the alternative GET endpoint for scripts, making the purpose unambiguous and specific.

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 by noting that polling works fine and that the same feed is available via a direct API endpoint for scripts and dashboards, implying when to use this tool vs the endpoint. It lacks explicit 'when not to use' or comparison to siblings, but the guidance is clear enough.

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

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

Annotations already indicate read-only and non-destructive behavior. The description adds substantial context: it fans out to multiple sources, has a fallback strategy, mentions an API sunset issue, and describes the return structure. This goes beyond what annotations provide, though the annotations already cover core safety 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?

The description is relatively long but tightly packed with useful information. It is well-structured: starts with usage examples, explains the tool's function, details parameters, output format, and alternative tools. Every sentence adds value, though some redundancy could be trimmed slightly.

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

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

Given the tool has 3 parameters with 100% schema coverage and no output schema, the description is highly complete. It explains the return format (changes grouped by source, total count, citation URIs) and covers edge cases like fallback and API sunset. It also differentiates from the sibling 'entity_profile', ensuring the agent understands scope.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaning by explaining that `since` accepts ISO dates or relative shorthand, gives examples ('7d', '3m', '1y'), and suggests a typical monitoring value ('30d' or '1m'). It clarifies that `type` only supports 'company' and `value` can be ticker or CIK. This adds 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 starts with example natural language queries ('What's new with X'), then clearly states it provides a change feed for a company in a specified time window, fanning out to SEC, GDELT/GNews, and USPTO. It specifies the `since` parameter format and distinguishes from the sibling tool 'entity_profile', making the purpose unambiguous.

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

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

The description explicitly says when to use this tool ('recent changes') and when to use 'entity_profile' instead. It also explains fallback behavior (GNews when rate-limited), USPTO soft-fail, and gives typical `since` values ('30d' or '1m'). This provides clear usage guidance and alternatives.

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

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

Annotations already indicate this is not read-only, not destructive, and idempotent. The description adds behavioral detail: data is scoped by identifier, persistent for authenticated users, 24hr for anonymous. This goes beyond the annotations and helps the agent understand memory lifetime and scoping.

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

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

The description is three sentences with no fluff. It front-loads the core purpose, then gives usage cues, and ends with companion tools. 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?

For a simple key-value store with two required parameters and no output schema, the description fully covers input semantics, storage behavior, and how to retrieve/delete. No gaps remain.

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?

Parameter descriptions in the schema are already clear (key and value). The description adds naming conventions for keys ('subject_property', 'target_ticker') and clarifies that value can be any text. This provides richer guidance beyond the schema.

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

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

The description clearly states the tool's purpose: save data for reuse across sessions. It gives concrete examples of use cases (resolved ticker, target address, etc.) and distinguishes itself from sibling tools like recall and forget by mentioning them as companions.

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

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

The description explains when to use the tool ('when you discover something worth carrying forward') and provides context about persistence (authenticated vs anonymous). It does not explicitly state when not to use, but the context is clear enough. It references companion tools recall and forget.

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. The description adds that each call cascades through several internal endpoints and auto-disambiguates company inputs. This provides useful behavioral context beyond the annotations, confirming safety and multiple internal calls.

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, starting with example questions, then stating the primary use case, followed by supported types and their returns. It is somewhat lengthy but each sentence provides important information. Minor conciseness improvement could be made by grouping related details.

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

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

Given the tool's complexity (multiple entity types, two parameters, no output schema), the description covers all essential aspects: what each type returns, acceptable inputs, auto-disambiguation, and the fact that it replaces multiple manual lookups. No gaps are apparent.

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%, but the description adds significant value: it explains the meaning of each type ('company' returns ticker, CIK, company_name, etc.) and clarifies valid inputs for the value parameter (ticker, CIK, or name for company; brand or generic for drug). This goes well beyond the schema descriptions.

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

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

The description starts with example queries like 'What's the ticker for...' which clearly illustrates the tool's purpose. It states the tool resolves a user-spoken name to a canonical identifier needed by other tools, using specific verbs and resources. It also distinguishes from siblings by emphasizing its role as a first-step lookup tool.

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

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

The description explicitly instructs to 'Use FIRST whenever you have a name but need an ID', providing clear when-to-use guidance. It also lists supported entity types and explains what each returns. However, it does not explicitly mention when not to use the tool or discuss alternative sibling 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 declare readOnly, openWorld, idempotent, non-destructive. Description adds specific behavioral details: probes each entity, ranks by score, surfaces most/least recognized, returns score/confidence/signal density. 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, front-loaded with action verb, no wasted words. 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?

Despite lacking output schema, description explains return values (ranked list with score, confidence, signal density) and input requirements (2-8 entities). Complete for a comparison tool given rich annotations.

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

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

Schema has 100% coverage, so baseline is 3. Description adds context that first entity is treated as 'subject' for narrative, enhancing 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 compares AI visibility across multiple entities, probes each with ai_visibility_check, and returns a ranked list. It distinguishes from sibling 'ai_visibility_check' by explicitly mentioning its multi-entity nature 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?

Provides a clear use case ('competitive AI-marketing audits') but does not explicitly state when not to use or list alternatives beyond implying multi-entity comparison.

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 (readOnlyHint, idempotentHint), the description explains partial failures, bundlephobia timing (5-30s first measurement), and graceful degradation with sources_failed field. It fully discloses non-obvious runtime behaviors.

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 front-loaded with purpose. While slightly long, every sentence adds unique value. Minor gains could be made by trimming, but structure is effective.

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

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

Given the tool's complexity (composite, multiple sources, timeouts) and no output schema, the description fully explains return format, behaviors, and edge cases. It is complete and self-contained.

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

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

Schema coverage is 100% with clear descriptions. The description adds value by noting scoped packages are accepted and version defaults to latest. This extra context earns above the baseline of 3.

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

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

The description clearly states the tool's purpose: a composite check for adding an npm package, combining deps.dev and bundlephobia data. It specifies the exact use case and output, distinguishing it from sibling tools that focus on other research topics.

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

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

Explicitly tells when to use: when an agent asks about package safety, popularity, size, or cost. Also mentions ecosystem limitation (NPM only in v1) and directs other ecosystems to deps.dev:version, providing 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 readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, providing safety and operational clarity. The description adds useful context about being keyless (no authentication needed) and the catalog's content, enhancing transparency beyond annotations.

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

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

The description is a single, front-loaded sentence with zero waste. Every part is informative and earns its place.

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

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

Given the tool has three parameters, rich annotations, and no output schema, the description covers the catalog source, keyless access, and example queries. It is sufficiently complete for a search tool, though pagination or result format details are omitted.

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 input schema already documents all three parameters. The description adds minimal extra meaning beyond the schema examples, meeting the baseline for high schema coverage.

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

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

The description clearly specifies the tool searches the USGS ScienceBase catalog, naming the resource and content types (datasets, publications, projects). It distinguishes from sibling tools like deep_research or search_within by targeting a specific government database.

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 via examples ('streamflow', 'earthquake hazard') and states it's keyless, but does not explicitly state when to use this tool over alternatives or provide any exclusions.

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

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

Discloses embedding model (BGE-base-en), similarity (cosine), window size (500-char overlapping), character cap (200K), and truncation behavior (truncated and flagged). All this goes beyond the provided annotations (readOnlyHint, etc.) and adds valuable 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?

Description is informative but somewhat verbose. It front-loads key information but includes technical details (embedding model, window size) that could be condensed. Each sentence serves a purpose, but overall length could be reduced without losing clarity.

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

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

Despite lacking an output schema, description adequately explains return values: top-N passages with character offsets and similarity scores, plus truncation flag. Given the tool's complexity (semantic search), this is sufficient for an agent to understand usage.

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

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

Schema coverage is 100% for all three parameters. Description adds meaningful extra context: for 'text' specifies max size and truncation; for 'query' provides example queries; for 'limit' states range and default. This supplements the schema descriptions.

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

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

Description explicitly states it performs semantic search inside a fetched record with specific examples (SEC 10-K, article) and outputs (top-N passages with offsets and scores). It distinguishes itself from sibling tools like ask_pipeworx_grounded.

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?

Clearly says when to use: when the record is too large for the prompt and to save context. Mentions pairing with ask_pipeworx_grounded. Does not explicitly state when not to use, but context implies usage for large documents.

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

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

Annotations indicate readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds behavioral context such as the OAuth requirement, return of subscription id, and delivery constraints (SMS cap, webhook auto-disable). 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 front-loaded with the main purpose and uses structured bullet points for types and delivery. Every sentence adds value, though it is slightly lengthy. Could be tightened but remains effective.

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

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

Given the tool's complexity (3 parameters, nested objects, no output schema), the description covers prerequisites, return value, type-specific params, delivery options, and constraints. No significant 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%, but the description adds significant meaning with concrete examples for each type and delivery options, including caveats like phone verification and signing secret. This enriches the schema descriptions.

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

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

The description clearly states the verb 'Create' and the resource 'proactive monitoring subscription to a live-data event stream'. It lists supported types with specific examples, 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?

The description specifies the prerequisite of a Pipeworx OAuth account and provides guidelines for delivery channels (SMS cap, phone verification, webhook auto-disabled). It does not explicitly state when not to use the tool, but the context is clear.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds value by explaining that the tool draws from a live catalog and returns structured example questions with exact tool+argument shapes.

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 efficiently packed with information, starting with example user queries. Every sentence adds value, though it could be slightly shortened without losing clarity.

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

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

Given no output schema, the description thoroughly explains the return value: category-bucketed examples with tool names and argument shapes. It also covers both invocation modes (with/without topic) and specifies when to use this tool first.

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

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

Schema coverage is 100% with a single optional topic parameter. The description adds meaning by explaining that omitting topic gives a full spread and passing a topic focuses the output, which goes beyond the schema 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 clearly states the tool as an onboarding entry point for new agents, specifying it returns category-bucketed example questions. It distinguishes itself from siblings by being the first tool to use when unsure of Pipeworx's capabilities.

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 guides the agent to use this first when it doesn't know what Pipeworx can do, and mentions optional topic parameter for focus. While it doesn't list alternatives, it does differentiate from siblings in context.

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

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

Annotations already indicate readOnlyHint=false, destructiveHint=false, idempotentHint=true. The description adds value by clarifying that the row is deactivated (not deleted) and ownership is enforced, providing behavioral context beyond annotations.

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

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

The description is two sentences, no wasted words, front-loaded with the main action, 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?

Given the tool's simplicity (one required param, no output schema), the description covers purpose, ownership constraint, and the deactivation behavior completely, with 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 description for the 'id' parameter. The tool description does not add new meaning beyond the schema's existing explanation, meeting the baseline for full 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 'Cancel a subscription by id', specifying the verb 'cancel' and resource 'subscription'. It distinguishes from sibling tools like 'subscribe' and 'list_subscriptions' by noting ownership enforcement and 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?

The description provides explicit guidance: 'Ownership is enforced — you can only cancel your own subscriptions'. It also hints at an alternative (recent_alerts) for historical events, though does not fully enumerate when not to use this tool.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive. Description adds value by disclosing returned verdict values, structured form, citation format, percent delta, and underlying data source (SEC EDGAR + XBRL). 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?

Two concise, well-structured sentences. First sentence defines use case with examples, second explains return details. Every sentence adds value without redundancy.

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

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

Given the tool has only one parameter and no output schema, the description fully covers what the tool does and returns, including verdict types and citation mechanism. No gaps for the agent.

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

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

Single parameter 'claim' has 100% schema coverage. Description provides natural-language examples reinforcing the schema description, adding practical usage context beyond the schema definition.

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

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

Description clearly states the tool's purpose: natural-language claim verification against authoritative sources. It lists example queries, specifies domain (company-financial claims via SEC EDGAR + XBRL), and distinguishes from siblings by noting it replaces 4–6 sequential calls.

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

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

Explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct' and mentions supported domain. While it doesn't explicitly list when not to use, the context and domain constraints are clear.

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