dogceo

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

The description discloses that the tool returns per-model score, confidence, signals, raw_response, and a combined view, adding context beyond annotations. It also notes that default model is free and Anthropic calls require user-paid key. No contradictions with readOnlyHint, idempotentHint, or destructiveHint.

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

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

The description is a single, well-structured paragraph of about 5 sentences. It front-loads the main purpose, then adds detail. Every sentence contributes 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 no output schema, the description adequately explains the return structure (per-model fields and combined view) and covers all parameters, defaults, and use cases. It is complete for a read-only, non-destructive 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?

All parameters have schema descriptions (100% coverage), and the description adds further meaning: default model value, Anthropic key purpose, and entity/context examples. This goes beyond the schema to clarify usage.

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 probes LLMs for knowledge about an entity and scores visibility (0-100) per model, specifying default model and optional Anthropic. This distinguishes it from sibling tools that focus on other tasks like asking specific questions or comparing entities.

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

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

The description explicitly lists use cases: AI-marketing audits, pre-launch brand checks, competitive monitoring. It also explains when to use the _apiKey parameter for Anthropic. However, it does not mention when to avoid this tool in favor of siblings or alternatives.

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

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

Annotations already provide readOnly and idempotent hints. Description adds useful internal behavior: routing to thousands of tools, filling arguments, and returning stable citation URIs. No contradiction with annotations. Does not mention rate limits or edge cases, but context is sufficient.

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, front-loaded with key preference, lists domains clearly, then explains mechanism, usage patterns, and examples. Every sentence earns its place; 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 (massive tool covering many sources) and no output schema, the description adequately explains the output type and purpose. Could be improved by detailing the output format or citing limitations, but it is complete enough for effective use.

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

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

Schema coverage is 100% with minimal descriptions for each parameter (all aliases for 'question'). The description only says 'Your question in natural language' and does not add nuance or syntax beyond the schema. Baseline 3 is correct.

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 states precisely what the tool does: it routes natural language questions to 3,769 tools across 891 verified sources and returns structured answers with citation URIs. It clearly distinguishes from web search and covers a wide range of factual domains.

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 recommends prefere over web search for authoritative data, lists trigger phrases ('what is', 'look up', etc.), gives concrete examples, and implies when to use (factual, structured data queries). Missing explicit when-not-to-use but still strong 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 declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds valuable context: extra LLM cost, detailed refusal reasons (not_in_source, no_tool_match, etc.), and the extraction process. 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?

Approximately 100 words, front-loaded with core purpose, and every sentence adds distinct 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 complexity of a hallucination-resistant answer mode, the description covers purpose, usage context, behavioral traits, return format, and refusal reasons. No output schema exists, but the description details output structure 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 well-documented aliases. The description does not add parameter details but compensates by detailing the return structure (answer, evidence, refusal_reason, etc.), which is absent in output 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 defines the tool as a 'Hallucination-resistant answer mode for high-stakes reads' that extracts answers solely from tool results, with explicit refusal reasons. It distinguishes itself from the sibling 'ask_pipeworx' for casual lookups.

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

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

Explicitly states when to use: 'whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts', with examples like financial verdicts. Also advises preferring 'ask_pipeworx' for casual lookups, providing clear usage boundaries.

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

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

The description goes far beyond annotations, detailing market resolution, classification, fan-out logic, response shapes, safety features (low-confidence short-circuit, closed market handling, wide spread warnings), and resolution-rule risk. Annotations already declare readOnlyHint and idempotentHint, which the description reinforces without contradiction.

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

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

The description is lengthy but well-structured with labeled sections (CLASSIFIERS, FAN-OUT EXAMPLES, RESPONSE SHAPES), making it scannable. Every sentence adds value for a complex tool, though it could be slightly trimmed 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?

The description covers all significant aspects: input types, classification, fan-out examples, response fields, safety mechanisms, closed market handling, resolution rules, and edge cases. Despite no output schema, the description provides enough detail for an agent to understand what the tool returns.

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 good parameter descriptions, but the tool description adds context for include_raw (when to use full payloads) and depth (quick vs thorough) through fan-out examples and response shape details. This extra information enhances understanding beyond the schema.

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

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

The description clearly states the tool researches a Polymarket bet by pulling Pipeworx data in one call, specifying inputs (slug, URL, question text) and outputs (evidence packet + comparison). It distinguishes itself from siblings by focusing on single bet research, as seen in usage examples like 'should I bet on X'.

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

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

The description provides explicit use cases: 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z"'. It does not explicitly state when not to use or mention alternatives, but the context 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?

Annotations already provide readOnlyHint, idempotentHint, destructiveHint. Description adds that it returns array of image URLs, which is consistent but does not significantly expand beyond annotations.

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

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

Two efficient sentences, front-loaded with purpose and usage. 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?

Tool is simple with 2 params, output schema exists, and description covers purpose, return type, and usage. Complete for its complexity.

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

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

Schema coverage is 100% with descriptions for breed and count. Description offers breed examples but no additional semantic 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?

Clear verb 'Get' and specific resource 'multiple dog photos for a specific breed'. Distinguishes from siblings like random_breed_image (single) and random_image (any breed).

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 when you need a gallery of one breed.' No when-not-to-use or alternative mentions, but context with siblings 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 readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds significant context: it specifies data sources (SEC EDGAR/XBRL for companies, FAERS for drugs), sorting by primary metric, and inclusion of citation URIs. It does not contradict annotations and goes beyond them by explaining data fetching 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?

Every sentence is purposeful. Starts with actionable query examples, then gives usage rule, then explains per-type behavior, sorting, and return format. No filler; dense but well-organized information.

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

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

Given the tool's complexity (two modes, multiple data sources, parallel call), the description covers core functionality, usage context, data sources, sorting, and output (paired data + citation URIs). There is no output schema, so description carries the burden, and it does so adequately. Minor omission: no mention of how to interpret the paired data beyond 'sorted by primary metric'.

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

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

Schema coverage is 100% with descriptions for both parameters. The description reinforces parameter meaning by providing examples for 'values' (tickers/CIKs for company, names for drug) and explains what data 'type' retrieves. This adds value beyond the schema's basic enum descriptions.

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

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

The description clearly defines the tool as performing side-by-side comparisons of 2-5 entities (companies or drugs) in a single parallel call, with specific query examples. It distinguishes itself from sibling tools like entity_profile by explicitly saying it replaces sequential lookups.

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

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

The description explicitly states 'ALWAYS PREFER over sequential single-pack lookups when comparing entities' and gives example comparison queries. It differentiates between company and drug use cases. However, it does not explicitly state when NOT to use it (e.g., for non-comparative queries), though the context strongly implies 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?

Beyond the annotations (read-only, open-world, idempotent), the description reveals key behavioral details: parallel execution, grounded answers with verbatim evidence and citations, explicit gaps for unanswered facets, pre-verified facts, and expected latency (15-60s). 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 the core purpose and process. It is relatively long but each sentence adds value: usage guidelines, requirements, expectations. Minor redundancy (e.g., 'grounded' appears multiple times) but overall efficient for the complexity. Could slightly trim but still 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?

Without an output schema, the description adequately covers the return: 'structured findings packet' with citations, confidence, source, etc. It also mentions gaps and pre-verified facts. However, it does not specify the exact structure or field names beyond examples, which might leave some ambiguity for the agent. Still, for a complex tool, it is fairly 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%, but the description adds significant meaning: for the 'depth' parameter, it explains the numeric mapping (quick=3, standard=5, thorough=8) and the payment requirement for 'thorough'. For 'question', it clarifies that natural language and multi-part questions are acceptable. This goes well beyond the schema's enum and type definitions.

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

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

The description clearly states it performs multi-source research by decomposing questions and routing to many tools in parallel. It distinguishes itself from the sibling tool 'ask_pipeworx' by specifying that it handles broad, multi-part questions, while ask_pipeworx is for single lookups. Specific verbs and resources are used ('Decomposes your question', 'extracts a grounded answer').

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 provides when to use this tool (broad/multi-part questions) and when to use an alternative (single lookups: use ask_pipeworx). Also mentions prerequisites: requires a Pipeworx account and a paid plan for 'thorough' depth. The description gives clear context for selection.

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

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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds that results include names, descriptions, and full input schemas with curated examples, and each result is ready to call directly. 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 4 sentences, front-loaded with purpose, then lists domains, explains output, and gives usage guidance. Every sentence is meaningful and adds value.

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

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

Given the tool's purpose of discovering other tools, the description fully explains input, output format, and when to use it. No output schema exists, but the description sufficiently describes what is returned.

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

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

Schema coverage is 100%. The description adds value by noting multiple aliases for 'query' (task, q, description, search) and specifying limit defaults and max. The schema itself also includes examples.

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

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

The description clearly states the tool finds tools by describing the data or task, provides specific domain examples (SEC filings, financials, etc.), and distinguishes itself from domain-specific siblings like 'deep_research' or 'compare_entities'.

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

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

The description explicitly says 'Call this FIRST when you have many tools available and want to see the option set (not just one answer),' giving clear when-to-use guidance. It also implies the tool is for browsing rather than when a specific tool is already known.

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

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

Annotations already indicate readOnly, openWorld, idempotent, and non-destructive behavior. The description adds valuable context: tool makes one parallel call, fans out across sources, and includes a soft-fail for USPTO. It does not contradict any 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 examples and a strong usage preference. It is detailed but every sentence adds value, covering limitations and output structure. Slightly verbose but effective.

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

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

Given the complexity of multiple data sources and fallbacks, the description thoroughly explains what the tool returns (specific fields and URIs), current limitations (USPTO soft-fail), and input constraints. No output schema exists, so the description adequately covers return values.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds meaning beyond schema: clarifies that only 'company' type is supported, explains value formats (ticker or zero-padded CIK), and provides examples (AAPL, 0000320193). It also reinforces the constraint on names.

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

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

The description clearly states the tool provides a 'full cross-source profile of a US public company in ONE parallel call' and lists specific data sources (SEC, XBRL, USPTO, news, GLEIF) and outputs (cik, filings, fundamentals, patents, news, LEI). It distinguishes itself 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 advises 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view.' It also specifies when to use 'resolve_entity' first if only a name is available, providing clear context for appropriate usage.

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

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

Annotations already provide destructiveHint=true and idempotentHint=true, indicating mutation and safe retry. The description adds context about clearing sensitive data, which aligns with the destructive nature. No contradictions are present.

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

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

The description is extremely concise with just two sentences, no filler. The main action is front-loaded in the first sentence, making it efficient for an agent.

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

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

The tool is simple with one parameter and no output schema. The description covers purpose, usage context, and pairing, which is sufficient. Annotations cover behavioral traits, so the description is complete for this complexity level.

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

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

Schema coverage is 100%, and the schema already describes the 'key' parameter as 'Memory key to delete'. The description only mentions 'by key' without adding new 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 'Delete a previously stored memory by key,' which is a specific verb+resource combination. It distinguishes from siblings 'remember' and 'recall' by explicitly mentioning 'pair with remember and recall.'

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

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

The description explicitly specifies when to use: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also suggests pairing with 'remember and recall', providing clear usage 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, openWorldHint, idempotentHint, and non-destructive. The description adds context by naming specific AI crawlers (ChatGPT, Claude, Perplexity), describing the output as 'standard llms.txt markdown format' and 'ready to drop at site-root/llms.txt', which explains the behavior beyond the annotations.

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

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

The description is three sentences, front-loading the main purpose and then adding detail. It is concise and wastes no words, though it could be slightly tighter.

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

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

Despite no output schema, the description explains the output format thoroughly (a single text blob, standard llms.txt markdown). It covers the process and use cases. For a simple tool with two parameters and clear annotations, the description is complete.

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

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

Schema coverage is 100%, so the description adds limited value over the schema. It gives an example for the url parameter and notes the default and max for max_links, but does not elaborate further. Baseline 3 is appropriate.

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

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

The description clearly states the tool generates a 'production-ready llms.txt file' for AI crawlers. It specifies the verb (generate), resource (llms.txt), and the process (fetch page, extract title/description/key links, emit markdown). This uniquely distinguishes it from sibling tools like ai_visibility_check or scan_competitor_ai_presence.

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: '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 implies when to use but does not explicitly state when not to use or directly compare 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, openWorldHint, and non-destructive. Description adds value by detailing return content (breed names and varieties, including sub-breeds), 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?

Two sentences, no waste. First sentence states core functionality, second sentence provides actionable usage guidance. Perfectly concise and front-loaded.

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

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

Given the tool's simplicity (0 parameters, rich annotations, output schema exists), the description fully covers purpose, return content, and use cases. 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?

Input schema has 0 parameters, baseline is 4. No parameter information needed; description correctly omits details about nonexistent 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 explicitly states 'List all available dog breeds and sub-breeds' with clear verb 'list' and resource 'breeds'. It distinguishes from sibling tools like breed_images by explaining use for exploration/validation before fetching images.

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

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

Description provides clear context: 'Use to explore breeds or validate a breed name before fetching images.' While it doesn't explicitly state when not to use, the context implies alternatives for image retrieval.

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

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

Annotations already declare the tool read-only, non-destructive, and idempotent. The description adds value by specifying the returned fields (id, type, params, timestamps, fire_count) and the default active-only behavior, which is not in annotations.

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

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

The description is concise with two sentences: first states purpose and return fields, second gives usage guidance. No fluff or redundancy; 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?

The description covers purpose, return fields, and usage context. It lacks mention of potential pagination or maximum results, which is a minor gap given no output schema. Overall, it is largely complete for a simple 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 1 parameter with a clear description (include_inactive, boolean, default false). Schema coverage is 100%, so the tool description adds no further parameter details. 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 the resource 'subscriptions', specifying the scope as 'caller's active subscriptions'. It explicitly distinguishes from sibling tools like subscribe and unsubscribe by its listing 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 provides clear guidance: use to review active subscriptions before adding more, or to find an id for cancellation. It implies when to use (before subscribe/unsubscribe actions) but does not explicitly state when not to use.

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

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

Annotations are all false but the description adds important behavioral details: rate-limited, free, doesn't count against quota, and that team reads digests daily. No hidden side effects are relevant. Lacks mention of anonymity or whether feedback is public, but still adds significant context beyond annotations.

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

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

The description is a compact paragraph with no wasted words. It front-loads the purpose and logically flows to usage guidance, constraints, and parameter tips. 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?

For a simple feedback tool with no output schema and three parameters, the description covers purpose, when to use, what to include, rate limits, and quota impact. It is fully sufficient for an AI agent to invoke 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 covers all parameters with descriptions (100% coverage). The description adds useful usage advice: 'Describe the issue in terms of Pipeworx tools/packs' and '1-2 sentences typical, 2000 chars max', which enhances understanding beyond the schema alone.

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

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

The description clearly states the tool is for sending feedback to the Pipeworx team about bugs, missing features, data gaps, or praise. It uses specific verbs and resources, and no sibling tools overlap with this purpose.

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 specifies when to use the tool: for bugs, feature requests, data gaps, or praise. Also provides guidance on what not to do (e.g., don't paste the end-user's prompt) and mentions the rate limit of 5 per identifier per day.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds caching behavior ('Cached 5min-1h depending on window') and sources ('derived from CF analytics-engine, no PII'), which provides additional transparency.

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

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

The description is front-loaded with the core purpose and use cases. At two sentences plus a bullet list, it's relatively compact, though the bullet list adds slight verbosity.

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

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

For a simple tool with one optional parameter, full annotation coverage, and no output schema, the description sufficiently covers purpose, usage, parameter nuance, and behavioral details like caching and PII safety.

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 the trade-off between short and long windows ('Shorter windows surface what's hot right now; longer windows show steady-state demand'), which goes beyond the schema's description.

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

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

The description states 'Returns the top tools, top packs, and total call volume over a recent window (24h, 7d, or 30d)', clearly specifying the verb, resource, and 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 lists three explicit use cases (discovering hot data sources, confirming canonical tools, aligning use case) and notes that shorter windows surface hot trends while longer show steady-state demand.

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 a read-only, idempotent tool. The description adds substantial behavioral context: required parameters, modes, monotonicity checks, partition filter, fill check against live depth, and realizable vs theoretical edge. There is no contradiction with annotations.

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

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

The description is detailed but well-structured. It starts with a critical requirement, explains modes, internal details, and response fields. Every sentence adds value, but it is slightly verbose and could be tightened 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 no output schema, the description thoroughly explains the response structure (opportunities[], partition_check, fill_check) and covers edge cases like no-arg calls, partition filters with placeholders, and fill check with thin legs. It references a sibling tool for custom sizing, making it comprehensive for a complex 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. The description adds clarity by explaining modes, giving example slugs and topics, and noting that full URLs are accepted for event. It goes beyond the schema by providing usage context.

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: finding arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes between event-mode and topic-mode, and differentiates from sibling tools like polymarket_edges and polymarket_fill_risk.

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

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

The description explicitly advises when to use event vs topic modes, warns that calling with no args fails, and notes that cross-event mode catches patterns missed by single-event. It also references polymarket_fill_risk for custom sizing. However, it does not provide explicit exclusions or comparisons to all sibling tools.

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

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

The description goes beyond annotations by detailing caching behavior (1h KV), response structure (by_segment, diagnostics, fed_note), and model family logic. It also warns about 24h move and Fed data limitations, providing rich behavioral context.

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

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

The description is thorough and front-loaded with purpose, but it is verbose with multiple paragraphs detailing model families and diagnostics. It could be more concise while retaining essential information.

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

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

Despite no output schema, the description thoroughly explains the response fields (by_segment, diagnostics, fed_note) and all available knobs. It covers filtering logic and edge cases, making it complete for a complex tool with 9 parameters.

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 parameter descriptions in the schema are already detailed. The tool description does not add significant additional meaning for parameters beyond what the schema provides, resulting in baseline score.

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: scanning Polymarket markets for opportunities where Pipeworx data disagrees with market price. It specifies the three model families and is built for daily bet discovery, effectively distinguishing it from sibling tools like polymarket_arbitrage.

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

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

The description provides clear context on when to use the tool (daily discovery) and explains the tradeable-edge knobs and filters. However, it does not explicitly compare against sibling tools or state when not to use this tool.

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

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

The description adds significant behavioral detail beyond annotations: it explains snapshot-based data, computed fields (trend, decay), expiration tracking, and nuances like decay from daily closes not intraday. There is no contradiction with annotations (readOnly, idempotent, not destructive).

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

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

The description is lengthy but well-structured: it starts with the core purpose, then details the response format, and ends with limitations. Every sentence adds necessary context; no fluff or repetition.

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 (2 optional params, no output schema), the description thoroughly explains the response structure (tracked, expired, snapshot_dates) and computed fields. It covers behavior, limitations, and data sources, making it complete for an AI agent to use.

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

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

Both parameters are documented in the schema (100% coverage), and the description provides additional context like default values, maximums, and the response structure that includes these parameters. This adds value beyond the schema alone.

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

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

The description clearly states the tool provides edge persistence and decay telemetry from daily snapshots, answering a specific trading question about edge age and decay. It distinguishes itself from sibling tools like polymarket_edges by focusing on time-series and computed trends.

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

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

The description explains when to use the tool (e.g., comparing fresh vs old edges) and provides context on data generation and limitations. However, it does not explicitly state when not to use it or list alternatives, though 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, etc. The description adds substantial behavioral detail: it walks the order-book ladder, returns specific fields (top_of_book, vwap_fill_price, slippage_pp, etc.), and explains behavior differences between single-market and basket modes, including risk signals like forced_directional_risk. 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 fairly long but efficiently packs all necessary information. It is front-loaded with the core purpose, then breaks down modes. Some repetition (e.g., REQUIRES statement repeated in explanation), but overall well-structured for the complexity.

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

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

With 4 parameters fully described in schema and rich description detailing return fields for both modes, including edge cases like thin_legs and forced_directional_risk, the tool is fully specified despite no output schema. Annotations provide safety context, making the description complete for agent decision-making.

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

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

Schema coverage is 100%, so baseline is 3. The description adds contextual meaning beyond schema: it explains the auto-default for side in basket mode, interprets size_usd as 'max spend on buys, target proceeds on sells' for single-market and 'settlement notional' for basket, and clarifies the OR requirement for market vs event. This adds meaningful value.

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

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

The description clearly states the tool performs a 'realizable-vs-theoretical edge check against live CLOB order-book depth', specifying the verb (check edge) and resource (order-book depth). It distinguishes itself from siblings like polymarket_arbitrage and polymarket_edges by explicitly stating it should be used before acting on their 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 explicitly advises 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500', providing clear context for when and when not to use this tool, along with rationale 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?

Discloses read-only, idempotent nature consistent with annotations; explains temporal alignment constraints, compatibility warnings, and leg-skipping reasons. 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?

Thorough but slightly verbose; well-structured with clear sections for modes, response, and safety fields. Every sentence adds value but could be tightened.

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?

Fully covers all aspects: modes, safety fields, temporal alignment, and warnings. No output schema needed given extensive description of response fields.

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

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

Schema coverage is 100%; description adds detailed usage context, enum values for topic, and examples for explicit parameters, exceeding schema alone.

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

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

The description clearly states the tool computes the spread between Kalshi and Polymarket for the same question, distinguishing it from siblings like polymarket_arbitrage and polymarket_edges which are intra-venue.

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

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

Explicitly describes two modes (topic and explicit), explains when safety warnings appear, and cautions that pre-mapped topics often yield incompatibility. Lacks explicit when-not-to-use, but warnings substitute effectively.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds 'Returns image URL and breed name', which adds minimal extra value. 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 key action, no wasted words. 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?

Simple tool with one parameter and output schema. Description explains return value, use case, and references list_breeds. Complete for the tool's complexity.

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

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

Schema coverage is 100% with description for 'breed' parameter including examples and cross-reference to list_breeds. Description does not add additional parameter information beyond schema.

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

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

Description uses specific verb 'get' and resource 'one dog photo for a specific breed' with examples. Clearly distinguishes from sibling tools like 'random_image' (generic) and 'breed_images' (plural).

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 you need exactly one photo of a particular breed' and references 'list_breeds' for valid values. Lacks explicit when-not guidance, 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?

The description says 'Get' which aligns with readOnlyHint=true, and it adds the return format (URL and breed name). However, it does not disclose additional behavioral traits beyond what annotations already provide (safety, idempotence). Since annotations carry the burden, the description adds moderate value.

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 with no fluff. Every sentence adds value: action, return, and usage context. Perfectly sized for a simple tool.

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

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

For a tool with no parameters, rich annotations, and an output schema, the description is complete. It covers purpose, output, and usage context, making it fully actionable 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?

With zero parameters and 100% schema coverage, the baseline is 4. The description does not need to add parameter info, and it provides meaningful context about what the tool does and returns.

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 'Get a random dog photo' with a specific verb and resource, and distinguishes from sibling tools by specifying 'without a specific breed preference', making it clear how it differs from breed-specific tools.

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

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

The description explicitly says 'Use when you need any dog picture without a specific breed preference', providing clear when-to-use guidance. It does not mention when not to use or alternatives, but for a simple tool this is sufficient.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint. Description adds scoping (by identifier), pairing with remember/forget for lifecycle, and the behavior of omitting key. No contradictions. Adds value beyond annotations.

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

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

Three sentences: first states core function, second gives use case, third adds scoping and pairing. No wasted words. Front-loaded with action and distinction.

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 low-complexity tool with 1 optional param, no nested objects, and good annotations, the description covers purpose, usage, and behavioral context. Could mention return value behavior (e.g., error if key missing), but not critical.

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

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

Schema coverage is 100% with one optional string parameter. Description clarifies that omitting key lists all keys, which adds contextual meaning beyond the schema's 'optional' indication. No further parameter details needed.

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 uses specific verb 'retrieve' and resource 'value saved via remember', and clearly distinguishes from sibling tools 'remember' and 'forget' by name. It also explains the alternate behavior when key is omitted (list all keys).

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?

States when to use (look up context without re-deriving) and what happens when key is omitted. Mentions sibling tools remember/forget as partners, providing context for alternatives. Could improve by explicitly stating when not to use, but otherwise 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 readOnly, idempotent, non-destructive. Description adds details on return fields (source, citation_uri, payload) and side effect of mark_read flagging events read. 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: purpose, output details, usage tips. 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?

Covers output format, filtering, mark_read behavior, polling suitability, and alternative access. No missing gaps for an alert-pulling tool with rich annotations.

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

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

Schema coverage is 100% with descriptions. The description adds context on filtering and mark_read effect but does not significantly enhance what the schema already provides. Baseline 3 is appropriate.

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

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

The description clearly states the tool 'pulls fired events from your subscription feed,' specifying the resource and action. It distinguishes from sibling tools like list_subscriptions and recent_changes by focusing on alerts/events.

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

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

Provides guidance on filtering by type and since, using mark_read, and polling behavior. Mentions an alternative access method via URL. However, lacks explicit exclusions or when-not-to-use scenarios.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context: the tool fans out to multiple APIs, handles fallbacks, accepts various date formats, and returns structured data with citation URIs. There are no contradictions.

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

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

The description is moderately long but well-structured, front-loading with example queries. Every sentence adds information about behavior, sources, or parameters. Slight room for more concise phrasing, 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 no output schema, the description specifies the return structure (changes[] grouped by source, total_changes count, pipeworx:// URIs). It also mentions the PatentsView API sunset and soft-fail behavior. For a complex multi-source tool, this is thorough and complete.

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

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

With 100% schema description coverage, baseline is 3. The description substantially enriches parameter meaning: it explains that 'since' accepts ISO dates or relative shorthand like '7d' or '3m', and 'value' can be a ticker or CIK. This goes beyond the schema's simple descriptions.

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

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

The description clearly states the tool's purpose: providing a change feed for a company in a specified time window. It lists specific sources (SEC EDGAR, GDELT→GNews, USPTO) and explicitly distinguishes from the sibling tool 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 provides explicit example queries that trigger the tool and directly states when to use entity_profile instead. It also explains fallback behavior (GDELT→GNews) and parameter format, giving clear guidance on tool selection.

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

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

Annotations already indicate idempotentHint=true, readOnlyHint=false, destructiveHint=false. The description adds valuable context: 'Stored as a key-value pair scoped by your identifier. Authenticated users get persistent memory; anonymous sessions retain memory for 24 hours.' This goes beyond annotations without contradicting 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 concise: three sentences, front-loaded with purpose, and every sentence adds value. No fluff or repetition.

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

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

The tool has two simple string params and no output schema. The description covers what it does, when to use it, and how it interacts with memory scoping and retention. Mentioning pairing with 'recall' and 'forget' completes the mental model. A small gap: no mention of storage limits or conflict behavior, but adequate for the complexity.

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

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

Schema description coverage is 100%, so the schema fully documents both parameters. The description adds usage context (e.g., storing findings, addresses) but doesn't provide additional syntactic or semantic detail beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states the purpose: 'Save data the agent will need to reuse later...across this conversation or across sessions.' It uses specific verbs (save, reuse) and resource (data), and distinguishes from siblings like 'recall' and 'forget' by mentioning pairing with them.

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

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

The description provides explicit usage context: 'Use when you discover something worth carrying forward...so you don't have to look it up again.' It also suggests pairing with 'recall' and 'forget'. However, it lacks explicit when-not-to-use conditions or alternatives, which keeps it from a perfect 5.

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

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

Annotations already cover safety and idempotency. Description adds significant context: internal cascading lookups, specific return fields per type (ticker, CIK, RxCUI, etc.), and auto-disambiguation for companies. No contradictions.

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

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

Description is moderately long but well-structured: starts with examples, then details supported types and behavior. Every sentence is informative, though could be slightly more compact without losing clarity.

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

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

Despite no output schema, the description thoroughly explains what is returned for each type, including citation URIs. Covers all necessary context for correct usage given the two-parameter input and internal complexity.

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

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

Schema coverage is 100% (baseline 3). Description adds meaning beyond schema by explaining accepted inputs (e.g., ticker, CIK, or name for company; brand or generic for drug) and implying the return value structure, which aids parameter usage.

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

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

Description explicitly states the tool resolves names to canonical IDs, gives clear examples like ticker, CIK, RxCUI, and distinguishes from siblings by noting it replaces 2-3 manual lookups.

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

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

Provides explicit guidance: 'Use FIRST whenever you have a name but need an ID.' Clearly describes supported entity types and their input formats. Could be more explicit about 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?

Beyond the readOnlyHint, openWorldHint, idempotentHint, and destructiveHint annotations, the description reveals internal behavior: it calls ai_visibility_check per entity, ranks by score, and returns confidence and signal density. 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?

Two well-structured sentences with zero waste. Front-loaded with the core action, followed by usage scenario and return format. 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 the complexity (4 parameters, no output schema), the description covers return format (ranked list, score, confidence, signal density) and the probing mechanism. It provides sufficient context for correct tool invocation without being exhaustive.

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

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

Schema coverage is 100%, and the description adds valuable context: first entity is treated as 'subject' for narrative, models are optional with default, and context disambiguates common names. This adds meaning beyond schema definitions.

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

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

Clearly states the tool compares AI visibility across multiple entities, probes each with ai_visibility_check, and returns a ranked list. Distinguishes from sibling tools like ai_visibility_check (single entity) and compare_entities (generic 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?

Explicitly says 'Useful for competitive AI-marketing audits' and gives a concrete example question. While it doesn't list exclusions or alternatives, the context is clear enough for an AI agent to decide when to use this tool over a single-entity check.

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?

Disclosed partial failures, bundlephobia latency (5-30s), and 'sources_failed' field. Annotations already mark readOnlyHint/idempotentHint, description adds beyond.

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?

Multiple sentences but each adds value. Front-loaded with purpose. Could be slightly tighter but still 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 complexity of multi-source scanning, description explains return fields, behavior on failure, and timing. No output schema but description compensates fully.

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

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

Schema covers both params fully. Description adds that version defaults to latest and scoped packages accepted. Slight additional 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?

Description clearly states it checks npm package safety, popularity, and size via deps.dev and bundlephobia. Distinguishes from sibling 'scan_competitor_ai_presence' and other tools.

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

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

Explicitly says 'use whenever an agent asks is X safe/popular/small' and notes NPM-only in v1 with fallbacks to deps.dev for other ecosystems.

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), search method (cosine), window size (500-char overlapping), and truncation cap (200K chars with flag) – adds significant behavioral context beyond annotations.

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

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

Single paragraph, no fluff, front-loaded with purpose, then usage, then technical details. 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, description explains return format (passages with offsets and scores) and pairs with another tool, covering all necessary aspects for effective use.

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

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

Schema coverage is 100%, and description reinforces parameter purposes with examples (query) and constraints (max chars, truncation flag). Slight deduction because it doesn't elaborate on the 'limit' parameter's default or format.

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, distinguishes from sibling tools like ask_pipeworx_grounded, and gives a concrete use case (record too big for prompt).

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 (record too big) and pairs with ask_pipeworx_grounded, providing clear guidance on 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 indicate idempotentHint=true and readOnlyHint=false. The description adds valuable behavioral details beyond annotations: OAuth requirement, phone verification for SMS, webhook signing secret returned only once, auto-disable after 10 failures, and that feed is always on. 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 a single dense paragraph but front-loaded with the primary purpose. Every sentence adds value, though the length may be slightly high. It is efficiently structured given the complexity of the tool.

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

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

Given the tool's complexity (3 parameters, nested objects, no output schema), the description is comprehensive. It covers subscription types, delivery options, constraints, and return value. Minor missing details like error handling do not detract significantly.

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 significant meaning by providing concrete examples for each type parameter, explaining delivery fields in detail (e.g., webhook HMAC signing, SMS verification), and clarifying constraints. It does not merely repeat 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 verb 'Create' and the resource 'proactive monitoring subscription' to a live-data event stream, and explicitly mentions the return value (new subscription id). It distinguishes from sibling tools like list_subscriptions and unsubscribe by focusing on creation.

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 using the tool: requires a Pipeworx OAuth account, lists supported types with examples, explains delivery channels, and notes constraints like phone verification and SMS cap. It does not explicitly compare with alternatives but gives enough detail for appropriate use.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint = true, and destructiveHint = false. The description adds context about being an onboarding tool and returning examples from a live catalog, but does not elaborate on behavioral traits beyond annotations. No contradiction.

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

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

The description is long and includes multiple example questions and a list of topics, which is informative but somewhat verbose. It is front-loaded with alternatives, but 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 simplicity (one optional parameter, no output schema), the description covers what the tool does, when to use it, what it returns, and how to invoke it. It also mentions the relationship to meta-tools, making it contextually 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% with a description for the `topic` parameter. The description provides example values (e.g., 'finance', 'pharma', 'betting'), which adds some value but does not significantly surpass the schema's own description. Baseline 3 is appropriate.

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

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

The description clearly states that the tool returns category-bucketed example questions with tool+argument shapes, and positions it as the onboarding entry point. It distinguishes itself from sibling meta-tools like ask_pipeworx, entity_profile, etc., by specifying when to use it first.

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

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

The description explicitly says to call with no arguments for a full spread or pass a topic to focus, and advises using this FIRST when the agent doesn't know what Pipeworx can do. It lacks explicit when-not scenarios, 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?

The description adds value beyond annotations by clarifying that the row is deactivated (not deleted) and historical events remain available. It aligns with destructiveHint=false. No contradiction is present.

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, front-loads the main action, and efficiently conveys constraints and behavior with no wasted words.

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

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

Given the single parameter, no output schema, and annotations, the description fully covers the tool's behavior, ownership constraint, and impact on historical data without needing additional 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% with the parameter 'id' described as 'Subscription id (uuid) returned by subscribe.' The description does not add additional meaning beyond the schema, so baseline score 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 action 'Cancel a subscription by id' with a specific verb (cancel) and resource (subscription). It is distinct from sibling tools 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 mentions ownership enforcement ('you can only cancel your own subscriptions') and explains the deactivation behavior. However, it does not explicitly state when not to use the tool or provide alternative tools.

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

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

Annotations already declare readOnly, openWorld, idempotent, non-destructive. Description adds return types (verdict, structured form, citation, percent delta) and explains it replaces multiple sequential calls, providing rich behavioral context.

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

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

Description is slightly long but front-loaded with examples and key information. Each sentence adds value, no redundancy.

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

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

No output schema exists, but description fully explains what the tool returns. Covers domain, usage, and behavioral aspects comprehensively.

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

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

Schema coverage is 100% with a good description. The description adds value by giving natural-language examples and clarifying the parameter's nature beyond the schema.

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

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

Description clearly states the tool verifies natural-language claims against authoritative sources, specifically company-financial claims. It gives example inputs and explains the output types, distinguishing it from other tools like compare_entities or 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 to use whenever the agent needs to check factual correctness, with a clear domain (company-financial). Does not explicitly mention when not to use, but the context is well-defined.

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