Box

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

Annotations already declare readonly, open-world, idempotent, non-destructive. The description adds that Workers AI is free, Anthropic requires a key passed through, and returns per-model fields. No contradiction with annotations.

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

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

Single, well-structured paragraph. Front-loaded with core purpose, followed by model details and use cases. Every sentence adds value, no filler.

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

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

Covers usage, parameters, output summary (per-model and combined). No output schema, but description adequately describes return structure. Adequate for complexity of 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%, so baseline is 3. Description adds value: default model is Workers AI Llama-3.3-70b (free), explains _apiKey is for Anthropic, clarifies context parameter purpose. Goes beyond schema.

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

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

The description uses specific verbs ('probe', 'score') and identifies the resource (LLMs for entity visibility). It clearly distinguishes from siblings like 'scan_competitor_ai_presence' by focusing on per-model scoring and audit use cases.

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

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

Explicitly states when to use: for AI-marketing audits, pre-launch checks, competitive monitoring. Mentions default model and optional Anthropic with key requirement, but doesn't discuss when not to use or compare directly with all siblings.

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

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

Annotations already indicate read-only, idempotent, non-destructive. The description adds value by detailing internal routing, citation format (pipeworx:// URIs), and that it returns structured answers. No contradictions or omissions.

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-organized with front-loaded key message, domain list, usage examples, and alternative hints. Some repetition (e.g., 'START HERE') but every sentence contributes.

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 complex routing tool, the description covers purpose, usage scenarios, output format (citations), and alternatives. Despite no output schema, it adequately describes the return value and provides multiple examples.

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

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

Schema coverage is 100% with descriptions for all 6 parameters (aliases). The description provides examples and context but does not add significant meaning 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 it routes factual questions to 4,482 verified sources, returning structured answers with citations. It lists many specific domains (SEC filings, FDA data, etc.) and distinguishes itself from web search and sibling tools like ask_pipeworx_grounded and deep_research.

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

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

Explicitly says 'PREFER OVER WEB SEARCH' and provides when-to-use examples ('what is', 'look up', 'find', etc.). It also advises when to step up to ask_pipeworx_grounded (hallucination-resistant) or deep_research (broad/multi-part). No misleading statements.

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

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

The description adds significant behavioral context beyond annotations: it discloses the extra LLM call cost, the return structure (including evidence, confidence, refusal_reason), and explicit refusal reasons. 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 and dense, with every sentence contributing value. Slightly verbose in listing aliases (already in schema), but overall well-structured and 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 format and failure modes. For a complex tool routing through 4,482 tools, the behavioral contract is complete and adequate.

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

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

Schema coverage is 100% with detailed descriptions for each parameter alias. The description does not add new information beyond noting aliases, which is already in schema. Baseline 3 is appropriate.

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

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

The description clearly identifies the tool as a 'hallucination-resistant answer mode for high-stakes reads,' specifies the routing and extraction process, and distinguishes it from the sibling ask_pipeworx. The purpose is unambiguous.

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

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

Explicitly states when to use this tool (when answers will be quoted, cited, or acted on) and when to prefer the sibling (casual lookups), including cost trade-off ('Costs one extra LLM call').

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?

Extensively discloses behaviors beyond annotations: resolver contract with match confidence, parent event extractor, news fields with fallback handling, safety mechansisms for low confidence and closed markets, tradeability warnings, cancellation rule parsing. Annotations already indicate read-only and idempotent, but description adds rich 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 quite long but well-structured with section headers and examples. While every sentence earns its place given the tool's complexity, it could be more concise for a typical tool description.

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?

Extremely complete: covers return shapes, edge cases, error states, safety mechanisms, and contract details. No output schema, but description effectively compensates by explaining response fields in detail.

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

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

Schema coverage is 100% with descriptions for all three parameters. Description explains parameter usage (e.g., market examples, depth options, include_raw behavior) but does not add significant meaning beyond schema. Baseline 3 is appropriate.

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

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

Clearly states the tool researches a Polymarket bet by pulling Pipeworx data in one call. Specifies input types (slug, URL, question) and processing steps. Distinguishes from siblings by focusing on comprehensive bet research with classifiers and evidence packet.

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 use cases: 'should I bet on X', 'what does the data say about Y', 'is there edge in Z'. Provides examples but lacks explicit when-not-to-use or direct comparison to siblings.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is clear. The description adds transparency by specifying the exact fields returned (id, name, size, description, etc.), which goes beyond annotations. No contradictions.

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

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

The description is two sentences with no wasted words. First sentence states action and resource, second sentence lists return fields and usage context. Every sentence 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 no output schema, the description compensates by listing return fields. It also provides usage context. However, it lacks potential error conditions or required permissions, but for a simple read operation it is sufficiently 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% and the parameter description 'The Box file id of the file to inspect' is already clear. The description reinforces that the file_id is the identifier, but adds no new semantic details 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: 'Get full metadata for a single Box file by its file id.' It lists the returned fields (id, name, size, etc.) and explicitly distinguishes from siblings like box_get_file_text by mentioning 'full metadata' and suggesting use after listing/searching.

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 gives explicit usage context: 'Use after listing or searching to inspect one document.' This tells the agent when to use this tool, though it does not explicitly list when not to use it or alternative tools. Still, the guidance is clear and helpful.

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 content cap of ~100,000 characters and truncation flagging, which adds behavioral context beyond the readOnlyHint and destructiveHint annotations. Warns about binary format limitations. 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?

Three concise sentences that front-load the core action, then add specificity about use cases and limitations. No extraneous information.

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

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

For a tool with one parameter and no output schema, the description fully covers what the agent needs: input, use cases, limitations, and truncation behavior. It is complete and actionable.

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 provides full description of the single parameter (file_id). The description does not add additional meaning beyond the schema's description, so baseline score of 3 is appropriate given 100% 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?

Description clearly states the tool downloads and returns text content of a Box file by file id, specifying the type of content it handles (plain-text, Markdown, CSV) and explicitly warning against binary formats. This distinguishes it from sibling tools like box_get_file without needing to name them.

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

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

Provides clear guidance on when to use (plain-text documents) and when not (binary formats yield unreadable bytes). However, it does not explicitly suggest alternative tools for binary files, leaving a slight gap in usage direction.

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, and safe operation. The description adds value by specifying the return fields and that it concerns the signed-in user, which goes beyond the annotations.

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

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

Two sentences, front-loaded with the action and resource, no unnecessary words. Highly efficient.

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

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

Given no parameters and no output schema, the description fully explains what the tool returns and why to use it. Nothing missing.

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

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

No parameters exist, so the description does not need to add parameter info. Schema coverage is 100%. Baseline score of 4 is appropriate.

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

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

The description clearly states the tool gets the signed-in Box user's profile with specific fields (id, name, email, storage). It distinguishes from sibling tools like box_get_file and box_list_folder by targeting user-level data.

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

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

The description provides explicit use cases: identify the connected account or report storage usage. It does not explicitly exclude other uses, but the context of no parameters and single resource makes it 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 safe, read-only behavior. Description adds value by specifying returned fields (id, type, name, size, last-modified) and default folder behavior, going 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, efficient and front-loaded with the core action. No redundant information.

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

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

Complete for a simple list tool. No output schema, but description clearly states what each returned item contains. Parameters well-documented in schema. No missing context.

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

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

Schema has full coverage for both parameters. Description restates folder_id default but does not add new semantic meaning beyond schema. Baseline 3 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?

Describes listing files and subfolders in a Box folder, with a specific verb and resource. Distinguishes from siblings like box_search and box_get_file by focusing on listing contents of a single folder.

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?

Explains how to use the tool by passing a folder_id or omitting it for root. Provides default behavior but does not explicitly contrast with alternatives like box_search.

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 clearly mark the tool as read-only, idempotent, and non-destructive. The description adds that it returns specific fields (id, type, name, size, last-modified time). No contradictions, and additional behavioral context enhances understanding.

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

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

The description is concise with four sentences, front-loading the main purpose and returning results. Every sentence adds value; no fluff.

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

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

Given the tool's simplicity, annotations, and full schema coverage, the description is largely complete. It explains the search scope (names and content), optional filters, and returned data. Could mention pagination via limit, but the schema already defines that.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds minimal extra meaning beyond the schema: it reiterates the type filter option and returned fields. No significant new parameter semantics.

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

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

The description clearly states the tool searches a user's Box account for files/folders using a query string across names and content, with optional type restriction. It distinguishes itself from siblings like box_get_file and box_list_folder by its generic search nature.

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 ('Use to find documents by keyword') and mentions optional filters, but does not explicitly state when not to use or provide alternatives like box_get_file_text. Still, the context is fairly 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 declare read-only, open-world, idempotent, non-destructive. Description adds specific behavioral details: for companies, pulls latest 10-K data with correct fiscal year handling; for drugs, pulls FAERS, FDA approvals, trial counts. Explains sorting by primary metric and return format (paired data + citation URIs), going well 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 information-dense but front-loaded with example queries. Every sentence contributes value. Slightly longer than minimal but justified by the tool's complexity. Efficiently packs many details without redundancy.

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

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

Given no output schema, the description adequately explains return values: paired data, citation URIs, sorted results. It covers input semantics, behavioral constraints, and output expectations. The tool is complex yet the description makes it clear for an AI 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%, but description adds valuable context: explains expected formats (tickers vs drug names), mentions max/min items, and describes what each type returns. It clarifies that for company, tickers or CIKs are used, and for drug, names. This enhances schema meaning.

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

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

The description clearly states the tool performs side-by-side comparison of 2–5 companies or drugs, with specific metrics for each type. It uses strong action verbs ('compare', 'rank') and distinguishes from siblings like entity_profile (single entity) and ask_pipeworx (general Q&A).

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' and provides example queries. Guides when to use (comparing entities) but does not explicitly state when not to use or mention alternatives beyond sequential lookups.

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 safe read idempotent behavior. The description adds context: never invents data (returns gaps[]), requires authentication, and specifies the return format (verbatim evidence, confidence, source, fetched_at, citations). 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 long but well-structured: critical usage constraints (account, alternatives) at the start, then functional details and expected behavior. Every sentence adds value, though some redundancy (e.g., repeating 'structured data sources') could be trimmed. Still, highly 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?

For a tool with 2 parameters and no output schema, the description fully explains purpose, usage, limitations, and return format. It covers all necessary context for an AI agent to correctly select and invoke this 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%, so baseline is 3. The description adds value by explaining the depth enum values (quick=3, standard=5, thorough=8) and reinforcing that the question should be broad/multi-part. This extra context justifies a 4.

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

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

The description explicitly states the tool performs 'grounded multi-source research across Pipeworx's 1129 structured data sources' by decomposing questions into facets and routing to 4,482 tools in parallel. It distinguishes from siblings like ask_pipeworx and clearly defines the scope.

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

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

The description provides explicit guidance: account requirements (free vs paid), fallback to ask_pipeworx if not signed in, preference for ask_pipeworx for single lookups and current news, and the expected latency (15-60s). This clearly differentiates when to use this tool versus 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, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral details about returning top-N tools with full schemas and examples, and that results are '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 detailed but somewhat verbose, listing many domains. While informative, it could be more concise without losing meaning.

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 meta-purpose, schema coverage, and annotations, the description adequately explains returns (top-N tools with schemas) and usage context. No output schema, but return value is described sufficiently.

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 parameters described. The description adds value by listing multiple aliases for the query parameter and providing natural language examples, enhancing understanding beyond the schema.

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

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

The description clearly states 'Find tools by describing the data or task' and provides a comprehensive list of domains (SEC filings, financials, etc.), making the purpose unambiguous and distinct from sibling tools.

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

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

Explicitly advises 'Call this FIRST when you have many tools available and want to see the option set,' providing strong usage context. It could be improved by explicitly stating when not to use it.

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

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

Annotations already declare readOnly, openWorld, idempotent, non-destructive. Description adds operational behaviors: parallel fan-out, patent data soft-fail date, 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?

Well-structured with example queries first. Slightly verbose but every sentence adds context. 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?

Covers tool actions, limitations (names not supported, patent soft-fail), and return fields. No output schema, but description lists returned data sufficiently for a profile 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 descriptions for both parameters. Description adds usage examples and clarifies naming limitation, but does not significantly extend 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 specifies a single verb-resource combination: provide a full cross-source profile of a US public company. It lists specific sources and output fields, and distinguishes from sibling tools like resolve_entity and compare_entities.

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

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

Explicitly states when to use ('holistic view') and when not to (single-pack lookups). Recommends using resolve_entity first if only name is available. Provides example queries.

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 destructiveHint=true and readOnlyHint=false. The description confirms deletion but adds no new behavioral details (e.g., irreversibility, permissions). 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?

Two sentences, front-loaded with the action, no wasted words. Every sentence serves a distinct purpose.

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

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

For a simple deletion tool with one parameter and full annotation coverage, the description provides sufficient context (use cases, pairing) without needing output schema details.

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 'key' parameter. The description only mentions 'by key' without adding substantive 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?

The description clearly states the action ('Delete a previously stored memory by key') and the resource ('memory'). It distinguishes from siblings like 'remember' (store) and 'recall' (retrieve).

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

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

Explicitly lists when to use: 'when context is stale, the task is done, or you want to clear sensitive data.' Also suggests pairing with 'remember' and 'recall', providing lifecycle context.

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

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

Annotations already declare readOnlyHint, idempotentHint, non-destructiveHint. The description adds beyond this: it fetches the page, extracts specific elements (title, description, key links), and outputs a 'single text blob' in standard markdown format. No contradictions.

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

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

The description is concise—three sentences that front-load the purpose, then detail the process, then list use cases. Every sentence adds value, no redundancy or fluff.

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

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

Given the tool's simplicity (2 params, no output schema), the description is fully complete. It explains the output format ('standard llms.txt markdown format', 'ready to drop at site-root/llms.txt') and the extraction process, compensating for the lack of output schema.

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

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

Schema description coverage is 100% for both parameters (url, max_links). The description does not add additional meaning beyond what the schema provides, such as format or constraints for 'max_links' (default 25, max 50). Baseline of 3 is appropriate.

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

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

The description clearly states the tool's purpose: 'Generate a production-ready llms.txt file for any URL' and explains the process (fetches page, extracts title/description/key links, emits standard markdown). It distinguishes from siblings like 'ai_visibility_check' and 'scan_competitor_ai_presence' by focusing on generation rather than checking or scanning.

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

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

The description explicitly lists use cases: 'getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.' It provides clear context for when to use the tool, though it lacks explicit when-not-to-use comparisons with siblings.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds context about return fields and an optional parameter, but no additional behavioral traits beyond what annotations cover. 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 with no wasted words. First sentence states purpose and return fields, second provides usage guidance. Efficiently structured.

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

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

Given the simplicity of the tool (one optional parameter, no annotations missing critical info), the description fully covers purpose, return values, and usage context. No output schema, but return fields are listed.

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

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

Schema coverage is 100% for the single parameter (include_inactive). The description does not add any additional meaning beyond what the schema already provides, so baseline score of 3 is appropriate.

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

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

The description clearly states the verb 'list' and resource 'subscriptions', specifies returned fields, and distinguishes from sibling tools like 'subscribe' and 'unsubscribe' by stating usage for review before adding or canceling.

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

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

The description explicitly tells when to use the tool: 'to review what you're monitoring before adding more or to find an id to cancel.' It provides clear context but does not include explicit exclusions or 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 provide limited behavioral hints (non-readOnly, non-idempotent). Description enriches this with rate limit details, roadmap impact, and quota exemption. No contradiction with annotations.

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

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

Single paragraph of 4-5 sentences. Front-loaded with purpose, then usage conditions, then critical notes. Every sentence serves a purpose; no filler.

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

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

Given no output schema and a simple void return, the description covers all necessary aspects: purpose, usage triggers, content guidelines, rate limits, and quota impact. It's fully self-contained for agent decision-making.

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

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

Schema covers 100% of parameters with clear descriptions. Description adds extra context: explains feedback categories concisely, advises message specificity, and sets length expectations (1-2 sentences, 2000 chars). Adds moderate value beyond schema.

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

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

The description clearly states 'Tell the Pipeworx team something is broken, missing, or needs to exist' and lists specific use cases (bug, feature/data_gap, praise). It effectively distinguishes itself from sibling tools that are query/action oriented.

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 with concrete triggers (wrong/stale data, missing tool, working well). Also gives negative guidance ('don't paste end-user prompt') and mentions rate limits and quota, 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 already indicate safe read-only, idempotent, non-destructive behavior. The description adds valuable context: self-aggregating signal from CF analytics-engine, no PII, and caching behavior (5min-1h). No contradictions.

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

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

The description is front-loaded with core functionality in three sentences followed by a focused bullet list. 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 simple parameter count, rich annotations, and no output schema, the description is complete. It explains the return items and caching, though could specify the output format more precisely.

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

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

Schema coverage is 100% with one enum parameter. The description adds meaning by explaining that shorter windows show current hotness and longer windows show steady-state demand, going 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 it returns top tools, top packs, and total call volume over a recent window, specifying the resource and action. It distinguishes from siblings like 'ask_pipeworx' and 'discover_tools'.

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

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

Three bullet points provide explicit use cases: discovering hot data sources, confirming a popular tool, and checking alignment with agent needs. Lacks explicit when-not to use, 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?

Disclosures go beyond annotations: describes walking child markets, checks, partition filter, fill check, response structure, and conditions for null arb signal. 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?

Dense and front-loaded but lengthy. Every sentence adds value, though could be more structured (e.g., bullet points). Appropriate for complexity.

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

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

No output schema, so description fully details response: opportunities array, partition_check fields, fill_check logic. Covers edge cases and trade recommendations.

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; description adds semantics: event slug examples, topic seed question examples, mode-specific behaviors. Adds value beyond schema.

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

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

The description clearly states it finds arbitrage opportunities via monotonicity violations + partition-sum checks. It distinguishes two modes (event and topic) and differentiates from sibling tools like 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 says 'REQUIRES one of event OR topic — call with no args fails.' Recommends event for specific markets, topic for cross-event scanning. Provides when-not-to-trade guidance and references polymarket_fill_risk for custom sizing.

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, and no destruction. The description goes far beyond these, detailing the three model families with formulas (e.g., 'lognormal barrier from 90d FRED log-returns'), edge calculation components (edge_pp_net, kelly_fraction), tradeable-edge knobs, caching (1h at KV level keyed on knobs), and diagnostics for empty segments. This fully reveals the tool's behavior.

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

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

The description is lengthy and dense with technical details. It front-loads the core purpose but then dives into extensive model descriptions, which could be condensed. While well-structured with sections (MODEL_DRIVEN, etc.), it is not concise. Every sentence adds value, but the overall length is high.

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 (9 parameters, 3 opportunity types, no output schema), the description is remarkably complete. It explains each model family's edge calculation, response structure (by_segment), diagnostics (e.g., filter_skips), caching behavior, and even why Fed bets are excluded. This level of detail compensates fully for the lack of output schema.

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

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

Schema description coverage is 100%, so baseline is 3. However, the description adds extra context beyond the schema for several parameters, such as explaining slippage_pp's default based on Polymarket fees and advising when to bump or drop it, and clarifying that min_partition_leg_kelly applies to per-leg Kelly while min_kelly does not filter partitions. This added value justifies a 4.

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

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

The description clearly states the tool's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It identifies the specific resource (Polymarket markets) and action (scan and return opportunities), and distinguishes itself from siblings like polymarket_arbitrage by focusing on Pipeworx data disagreement.

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

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

The description provides clear context for use: 'Built for "what should I bet on today"' and explains how to use knobs like min_liquidity, max_spread_pp, and min_partition_leg_kelly. It advises when to adjust slippage_pp and warns about Fed bets. While it doesn't explicitly state when not to use it or mention alternative tools, the context is sufficient for an agent.

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. Description adds significant behavioral details: return structure (tracked, expired, snapshot_dates), trend computation, limitations (60-day TTL). No contradiction with annotations.

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

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

Description is dense but well-structured. Front-loaded with core purpose. Could be slightly more concise, but every sentence adds value.

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

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

Thoroughly explains output fields and limitations despite no output schema. Completely covers what the agent needs to know 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%, so baseline is 3. Description mentions defaults and max but does not add substantial meaning beyond the schema parameters.

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

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

Description clearly states the tool's purpose: 'Edge persistence and decay telemetry' and answers the specific question 'how long has this edge existed and is it shrinking?'. It uses a specific verb and resource, and distinguishes from sibling tools like polymarket_edges.

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

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

Provides clear context on when to use: comparing fresh vs old edges. Does not explicitly state when not to use or list alternatives, but the purpose is well-defined.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the bar is lower. The description adds value by explaining the tool walks the order book ladder, returns specific fields (e.g., top_of_book, vwap_fill_price, slippage_pp), and warns about forced directional risk. 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 labeled sections (REQUIRES, SINGLE-MARKET, BASKET, USE THIS) and front-loaded purpose. While fairly long, every sentence adds value; no redundancy. Minor verbosity in details but overall efficient.

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

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

Given the complexity (two modes, multiple return fields) and no output schema, the description is comprehensive. It explains all key return data (e.g., verdict, capture_ratio, profit_usd, thin_legs) and the risks of partial fills and directional exposure. Sufficient for an agent to understand 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%, so baseline is 3. The description adds meaning beyond schema by explaining the difference between single-market and basket modes, default side logic (auto for basket), and interpretation of size_usd for each mode. This aids correct invocation.

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

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

The description clearly states the tool does a 'Realizable-vs-theoretical edge check against live CLOB order-book depth' (specific verb+resource) and distinguishes two modes (single-market and basket). It explicitly differentiates from siblings by instructing usage before acting on polymarket_arbitrage signals.

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: 'Use this before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also explains when not to rely on theoretical edge by warning about partial fills and directional risk.

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, nondestructive. The description adds extensive behavioral context: compatibility_warning conditions (non-equivalent bet shapes, semantically unrelated events), temporal alignment, skipped type counters. It does not contradict annotations and provides rich transparency beyond them.

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

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

The description is relatively long but well-organized: purpose, modes, response, safety fields. Front-loaded with the core purpose. Every sentence provides distinct value, though some details like the exact list of topics could be 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?

Given the tool's complexity (two modes, safety fields, temporal alignment) and no output schema, the description covers key aspects thoroughly. It explains response fields like compatibility_warning, skipped_cross_type, and temporal_alignment. Minor gap: response structure of spread array is not fully specified, but overall complete for an AI agent.

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

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

Schema coverage is 100%, so baseline is 3. The description adds significant meaning: lists the exact 10 topic shortcuts, explains override behavior for explicit tickers, and provides examples. This exceeds bare schema descriptions, 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 it computes cross-venue spreads between Kalshi and Polymarket for the same resolving question. It distinguishes from siblings like polymarket_arbitrage by focusing on cross-venue comparison. The verb 'cross-venue spread' is specific and the resource is well-defined.

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 two modes (topic vs explicit) and provides context for when to use each. It warns that most pre-mapped topics return compatibility_warning, indicating when spreads may not be tradeable. However, it does not explicitly mention alternative tools or when not to use the 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 value beyond annotations by explaining the scoping (to identifier) and the listing behavior when key is omitted. Annotations already confirm read-only and non-destructive, and description is consistent.

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, no wasted words. Front-loaded with the main action, then usage guidance, then pairing with other tools. Efficient and clear.

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

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

Given low complexity (one optional parameter, no output schema, detailed annotations), the description covers purpose, scope, pairing, and behavior. 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?

With 100% schema coverage, the baseline is 3. The description adds semantic meaning by listing example key values (ticker, address, notes), enriching the schema description which only says 'omit to list all keys'.

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

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

The description clearly states the tool retrieves a value saved via remember or lists all keys. It provides concrete examples of use cases (ticker, address, research notes) and distinguishes from siblings 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 'Use to look up context the agent stored earlier' and mentions pairing with remember/forget. It does not explicitly state when not to use, but the context is clear and covers the primary use case.

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 states 'Set mark_read:true to flag returned events read', which modifies state. This contradicts the annotation readOnlyHint=true, which indicates no side effects. The description adds context but contradicts annotations, so score is 1.

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, front-loaded with the purpose, and each sentence adds essential information without redundancy.

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

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

Given 5 parameters, no output schema, and annotations present, the description covers purpose, parameters, behavior, and alternative access. It mentions fields in the return value but lacks detail on pagination or error handling, which is acceptable for this simplicity.

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

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

Schema coverage is 100% (baseline 3). The description adds value by giving examples like 'sec_8k' for type and explaining that mark_read affects subsequent calls, which goes beyond 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 'Pull' and the resource 'fired events from your subscription feed'. It distinguishes from sibling tools like 'list_subscriptions' by specifying it returns alerts, not subscriptions.

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 usage context: 'Polls work fine' and mentions an alternative endpoint for scripts/dashboards. It does not explicitly state when not to use or compare to siblings, 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=true, idempotentHint=true, destructiveHint=false. The description adds rich behavioral detail: sources (SEC EDGAR, GDELT→GNews fallback, USPTO), fallback logic, PatentsView API sunset note, and return structure (changes[] grouped by source, total_changes, citation URIs). No contradictions with annotations.

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

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

The description is a single dense paragraph but front-loads with user query examples, states purpose, details sources, parameter guidance, and alternative. Every sentence adds value, no fluff.

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

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

Given the tool's complexity (multi-source, fallback, multiple parameters) and no output schema, the description covers purpose, sources, parameter formats, alternative, and return structure. It is complete for effective agent invocation.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds meaning: for `since`, it explains ISO vs relative shorthand with examples and a recommendation. For `value`, it explains ticker or CIK. For `type`, it notes only 'company' is supported. This adds value beyond the schema's minimal 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 clear query examples ('What's new with X', 'latest on Y'), then explicitly states the tool is a 'change feed for a company in the last N days/weeks/months in ONE parallel call'. It distinguishes from the sibling tool `entity_profile` by noting that tool is for static profiles.

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 context on when to use this tool (for changes over a time window) and when to use the alternative `entity_profile` (for static profile). It also gives guidance on the `since` parameter (ISO date or relative shorthand, recommends '30d' or '1m').

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 context beyond annotations: persistent vs 24-hour retention, scoped by identifier. Annotations already indicate idempotent and non-destructive, but description enriches with specifics.

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

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

Four well-structured sentences, each serving a purpose. Front-loaded with main action and usage context, 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?

Covers storage behavior and retention. No output schema, but return value (e.g., success) is not described. Minor gap for an otherwise complete description.

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

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

Schema coverage 100%, and description provides example values for 'key' (e.g., 'subject_property') and explains 'value' as any text, adding 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 the verb 'Save' and resource 'data' with context 'reuse later'. It distinguishes from siblings by mentioning 'recall' and 'forget'.

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

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

Explicitly tells when to use: 'when you discover something worth carrying forward'. Also mentions pairing with recall and forget, providing clear guidance.

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

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

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable behavioral context: internal cascading through multiple lookup endpoints and that one call replaces 2-3 manual lookups. It also explains return types per entity type, going beyond annotations.

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

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

The description is well-structured: starts with example queries, states the primary use case, then details supported types. Every sentence contributes value, and there is no redundancy. It is appropriately sized for the tool's complexity.

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

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

Despite lacking an output schema, the description thoroughly explains what each entity type returns (e.g., ticker, CIK, company name, citation URI). It also mentions internal cascading and the efficiency gain. For a simple entity resolution tool with only two parameters and full annotations, the description is complete and leaves no obvious 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?

Both parameters are already described in the schema (100% coverage). The description enriches understanding by providing concrete examples of acceptable values (e.g., 'AAPL', '0000320193', 'ozempic') and explaining the return content for each type. This adds meaning beyond the basic 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: resolving a user-spoken name to the canonical/official identifier needed by other tools. It provides specific examples ('ticker for...', 'CIK for...') and explicitly says to use it 'FIRST whenever you have a name but need an ID.' This distinguishes it from sibling tools like compare_entities or entity_profile.

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 gives clear usage guidance: 'Use FIRST whenever you have a name but need an ID.' It also details supported types and what each returns. While it doesn't explicitly state when not to use it or list alternatives, the recommendation is strong and sufficient for this resolution 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds that it iterates over entities, calls ai_visibility_check per entity, and returns a ranked list with score, confidence, and signal density. This clarifies the operation without contradicting annotations.

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

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

The description is three concise sentences: core action, mechanism, and usage example. No redundant information; every sentence adds value.

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

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

Given no output schema, the description specifies the return type (ranked list with score, confidence, signal density per entity). Parameters are fully documented in the schema, and annotations cover safety. The description covers all essential aspects for an agent to use the tool correctly.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds value by explaining the 'entities' array: first entry is treated as 'subject' and rest as competitors. This semantic detail aids correct invocation.

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

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

The description explicitly states the tool compares AI visibility across multiple entities, probes each with ai_visibility_check, and ranks them by score. It distinguishes itself from the sibling tool ai_visibility_check (single entity) by focusing on side-by-side comparison.

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

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

The description provides a clear use case ('competitive AI-marketing audits') and an example query. While it doesn't explicitly state when not to use it, the context implies it's for multi-entity comparison, not single entity checks.

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

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

Annotations already indicate read-only, open-world, idempotent, non-destructive. The description adds valuable behavioral context: partial failures degrade gracefully, bundlephobia's first measurement can take 5-30s, and sources_failed will list timeouts. 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 long but every sentence adds value. It front-loads the composite nature, then usage, then return summary, then ecosystem scope, then error behavior. Slightly verbose but well-organized.

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

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

Given no output schema, the description thoroughly covers return values (summary block, per-advisory detail, links, alternative versions) and error handling (partial failures, timeout behavior). Complex tool with rich context provided.

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

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

Schema coverage is 100% with descriptions for both 'package' and 'version'. The description adds minimal extra: mentions scoped packages accepted and default version behavior. Baseline 3 is appropriate as schema already provides meaning.

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

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

The description clearly states it's a composite check for npm packages, combining deps.dev and bundlephobia data, with a specific verb 'scan' and resource 'dependency'. It distinguishes from siblings like 'deps.dev:version' and other scan tools.

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

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

Explicitly says when to use it: 'whenever an agent asks is X safe / popular / small or what does adding lodash cost me'. Also provides exclusions: NPM only, and mentions alternatives for other ecosystems (PyPI, Maven, etc.).

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), chunking strategy (500-char overlapping windows), character offset verification, and truncation cap (200K chars with flag). All beyond what annotations provide (readOnlyHint, idempotentHint, etc.). 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?

6 efficient sentences with no redundancy. Front-loaded with purpose and usage, then technical details. Every sentence 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?

Despite no output schema, the description fully explains return values (top-N passages with character offsets and similarity scores). All necessary information for an agent to use the tool correctly is present.

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 repeats some schema details (max chars, limit range) but does not add new parameter meaning beyond the schema. Examples for query are helpful but not extra semantic depth.

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

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

Clearly states 'Semantic search INSIDE a fetched record' with specific verb 'search within' and resource 'source'. Distinguishes itself from siblings by describing when to use (large records) and pairing with 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?

Explicitly says 'Use when the record is too big to cram into the prompt' and provides an alternative workflow: 'Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document'.

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 many behavioral traits: returns subscription id, requires OAuth, delivery channels with constraints (SMS 10/day, webhook auto-disable after 10 failures, signing secret). 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?

Front-loaded with core purpose, then types, then delivery details. Dense but efficient; every sentence adds value. Slight length justified by complexity, though could be more structured (e.g., bullet points).

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

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

Covers return value, all types/params, delivery channels, and limitations. With no output schema, description explains what to expect. Minor omission of error scenarios and explicit mention of idempotency (though annotation says idempotentHint true).

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

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

Adds significant meaning beyond schema: per-type examples and constraints (e.g., sec_8k item codes, clinical_trial requirements), and detailed delivery object descriptions (webhook signing, SMS verification). Schema coverage 100% but description enriches it.

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 'Create a proactive monitoring subscription to a live-data event stream' with verb and resource, lists supported types, and implicitly distinguishes from siblings 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?

Provides context on when to use (proactive monitoring), requirements (OAuth account), and limitations (SMS cap, webhook auto-disable). Lacks explicit when-not or direct comparison to sibling tools like 'recent_alerts' for pulling alerts.

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

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

Annotations already indicate readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context by explaining the return format (category-bucketed example questions with tool shapes) and that calling with no arguments yields a full spread. 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 front-loaded with alternative phrasings of user intent, then provides a clear explanation of functionality and usage. While it is somewhat lengthy, every sentence provides useful information appropriate for an onboarding tool. No wasted words.

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

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

Given the absence of an output schema, the description adequately explains the return value: 'Returns category-bucketed example questions ... each with the exact tool + argument shape'. It also lists the categories and mentions that it draws from the live catalog. The description is sufficient for an agent to understand what to expect.

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

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

The single parameter `topic` is fully described in the schema (100% coverage). The description reinforces its meaning and provides concrete examples of values like 'finance', 'pharma', 'betting', which adds practical guidance 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 is an onboarding entry point that returns category-bucketed example questions with tool+argument shapes. It distinguishes itself from sibling tools by explicitly saying 'Use this FIRST when you do not yet know what Pipeworx can do for you' and listing meta-tools like ask_pipeworx as alternatives.

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 this tool first when unfamiliar with Pipeworx, and provides guidance on using the optional `topic` parameter to focus on a category. It doesn't explicitly state when not to use it, but the context is clear enough that this is an exploratory tool before using more specific 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?

The description adds important behavioral context beyond annotations: the row is deactivated (not deleted), preserving historical events via recent_alerts. This aligns with destructiveHint=false and idempotentHint=true, with no contradictions.

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

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

Two sentences, no wasted words, front-loaded with the primary action. 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?

With a single parameter and no output schema, the description covers purpose, behavior, ownership, and side effects, making it complete for this 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?

The input schema has 100% coverage with a description for the 'id' parameter mentioning it is returned by subscribe. The description does not add further detail, but the schema already provides sufficient meaning.

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

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

The description clearly states the action: 'Cancel a subscription by id.' It specifies the resource (subscription) and scope (your own subscriptions), distinguishing it from siblings like 'subscribe' and 'list_subscriptions'.

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 'Ownership is enforced — you can only cancel your own subscriptions,' providing a clear when-to-use condition. It does not explicitly discuss when not to use or mention alternatives, but the ownership constraint is a strong guideline.

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, destructiveHint false. The description adds value by explaining the return data (verdict, extracted form, actual value with citation, percent delta) and that it replaces multiple sequential calls. 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?

Well-structured: opens with example queries to quickly convey purpose, then scope, capabilities, and return format. Could be slightly more concise, but every sentence adds value; no fluff.

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

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

Given the single parameter, rich annotations, and no output schema, the description comprehensively covers scope, supported claim types, return format, and efficiency benefits. No gaps for an agent to misuse it.

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

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

Schema coverage is 100% with one parameter 'claim' already described. The description adds examples ('Apple's FY2024 revenue was $400 billion') and clarifies the natural-language nature, enhancing semantic understanding beyond the schema.

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

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

The description starts with natural language examples ('Is it true that...', 'fact check'), clearly states it is for claim verification against authoritative sources, and specifies scope (company-financial claims). It distinguishes from siblings by noting it replaces 4-6 sequential calls, making its purpose very specific and 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 'Use whenever the agent needs to check whether something a user said is factually correct.' Provides scope of supported claims (company-financial). However, no explicit when-not or alternative tools mentioned; siblings like ask_pipeworx_grounded might overlap but not addressed.

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