Libretranslate

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

Annotations indicate read-only, idempotent, non-destructive behavior. The description adds that it probes LLMs, returns per-model scores, and explains the default model and optional Anthropic usage with BYO key. It does not contradict annotations and provides valuable behavioral context beyond annotations.

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

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

The description is two sentences: first summarizes the core function, second provides usage details. Every sentence serves a purpose with no redundancy. It is front-loaded and appropriately sized.

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 return structure (per-model score, confidence, signals, raw_response + combined view). The required parameter, optional parameters, and their purposes are all covered. The tool is complex but the description fully addresses its usage.

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

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

Schema description coverage is 100%, so baseline is 3. The tool description adds value by explaining the default model, the role of the API key (BYO key, pay directly), and the context parameter's purpose for disambiguation. This extra information warrants a 4.

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

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

The description clearly states the verb 'probe', the resource 'LLMs for knowledge about an entity', and the output 'score visibility (0-100) per model'. It distinguishes itself from siblings like 'scan_competitor_ai_presence' by focusing on general AI visibility scoring across multiple models.

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

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

The description provides explicit guidance on when to use (AI-marketing audits, pre-launch brand checks, competitive monitoring) and how to customize (default free model, optional Anthropic with API key). It lacks explicit when-not-to-use or direct comparison with alternatives, but the context is clear.

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

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

Annotations already declare readOnly, openWorld, idempotent. Description adds value by explaining it routes to many tools, fills arguments, and returns structured answers with citation URIs. 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 front-loaded with key preference instruction, then lists domains, functionality, usage patterns, and examples. Some redundancy but overall clear and well-structured.

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

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

Description explains the routing and structured answer with citation URIs, but lacks details on output format, error handling, or behavior when no matching source found. No output schema to compensate.

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

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

Schema coverage is 100% with detailed parameter descriptions. Description provides examples and natural language hints, but these largely overlap with schema's examples and description. Minimal 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?

Description clearly states the tool answers factual questions using structured data from many sources, and explicitly says to prefer it over web search. Distinguishes itself from a general web search by listing specific use cases and domains. Provides examples of queries.

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

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

Description provides explicit guidance on when to use (prefer over web search for factual data) and gives query patterns. However, it does not compare to sibling tools like entity_profile or validate_claim, nor does it state when not to use it.

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

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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint false, openWorldHint true), the description adds behavioral details: extra LLM call cost, refusal reasons (e.g., not_in_source, no_tool_match), and behavior when data doesn't directly answer. 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 substantive but well-structured with front-loaded key purpose and usage. Every sentence provides value, though slightly verbose due to comprehensive detail; still appropriately sized.

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 return structure (answer, evidence, confidence, etc.) and all possible refusal_reason values. High complexity (3,744 tools, 884 sources) is addressed with sufficient detail.

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

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

Schema coverage is 100% with clear descriptions for the 'question' field and aliases. The description does not add further parameter semantics beyond what is already in the schema, which is sufficient for baseline 3.

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

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

The description clearly states it's a hallucination-resistant answer mode for high-stakes reads, specifying the routing and extraction process. It distinguishes from sibling 'ask_pipeworx' by noting extra LLM call and use case.

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

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

Explicitly states when to use: 'whenever an answer will be quoted, cited, or acted on' and lists example high-stakes domains. Also advises preferring 'ask_pipeworx' for casual lookups, providing clear 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 read-only, idempotent, open-world, and non-destructive behavior. The description adds substantial behavioral context: explaining market resolution, classification, parallel fan-out, safety mechanisms (low-confidence blocks, closed market detection, wide-spread warnings), and error handling (GDELT 429s). 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 overly long and includes extensive examples, classifier lists, and detailed response shapes. While well-structured with ALL-CAPS section headers, it could be more concise. Not every sentence is essential for typical tool usage.

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 compensates thoroughly by detailing response fields (market, analysis, evidence, resolver contract, parent event, news) and covering edge cases (low-confidence, closed markets, wide spreads). It is complete and self-contained.

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

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

Schema coverage is 100% with descriptions for all three parameters. The description enriches these, especially for 'market' (accepts slug, URL, or question text), 'depth' (quick vs thorough), and 'include_raw' (explains response size trade-offs). This goes beyond the schema baseline.

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

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

The description clearly states the tool's purpose: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It provides specific verb and resource, and includes usage examples (slugs, URLs, question text) and common use cases ('should I bet on X'), effectively distinguishing its role among siblings.

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

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

The description explicitly recommends use for three scenarios and provides 'when to use' guidance. However, it does not directly contrast with sibling tools like 'polymarket_edges' or 'validate_claim', leaving some implicit differentiation. Still, 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 significant context beyond annotations: it explains data sources (SEC EDGAR/XBRL, FAERS), handles off-calendar fiscal years, mentions sorting by primary metric, and notes return format with citation URIs. Annotations already declare read-only, idempotent, non-destructive; the description aligns and enriches with these details. 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 paragraph that effectively front-loads the purpose, then provides useful details. Every sentence adds information, though it could be slightly more structured with bullet points for the entity types. Overall it is concise without missing key aspects.

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

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

Given there is no output schema, the description adequately explains return values (paired data with citation URIs) and sorting behavior. It covers both entity types with sufficient detail for an agent to understand what information to expect. No significant gaps.

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

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

Schema covers both parameters with descriptions. The description adds value by elaborating on valid values (tickers/CIKs for company, drug names), constraints (2-5 items), and the behavior of the 'type' parameter with concrete examples. Since schema coverage is 100%, baseline is 3; the extra examples and constraints justify a 4.

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

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

The description clearly states the tool performs side-by-side comparisons of 2-5 companies or drugs. It uses specific verbs like 'compare' and 'rank', and distinguishes itself from single-entity lookups by explicitly advising preference over sequential calls.

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

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

The description provides explicit guidance on when to use this tool (comparing 2-5 entities) and advises preferring it over sequential lookups. It lists example user queries. However, it does not explicitly state when not to use it, such as for single entity details or non-comparative analysis.

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

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

Beyond annotations (readOnly, idempotent, etc.), description reveals decomposition, parallel execution across many sources, evidence format with gaps array, and expected duration (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?

Description is thorough but not excessively long. It front-loads core functionality and organizes details logically. A minor reduction in detail could be made, but every sentence contributes value.

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

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

Despite no output schema, description details the return format (structured findings packet with evidence, citations, gaps). For a complex tool, this covers what the agent needs to know about outputs and behavior.

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

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

Schema has 100% coverage, but description adds meaning for both parameters: explains what each depth value entails (number of facets) and that 'question' accepts broad/multi-part input naturally.

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 'Grounded multi-source research' by decomposing questions into sub-questions and extracting evidence. It distinguishes itself from sibling tool 'ask_pipeworx' by noting it handles broad/multi-part questions.

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

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

Explicitly guides when to use this tool (broad/multi-part questions) and when to use 'ask_pipeworx' (single lookups). Also mentions prerequisites (Pipeworx account) and depth limitations (paid plan for 'thorough').

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

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

Annotations already indicate read-only, idempotent, non-destructive. Description adds useful context about returning ranked candidates with confidence, which goes 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 concise sentences with no wasted words. Front-loaded with purpose and immediate behavioral output.

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, good annotations, and expected output schema, the description is sufficient. It covers what it does and what it 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 parameter 'text' already described. Description does not add additional semantics beyond what the schema provides.

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

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

Clearly states the tool detects language of text, with specific verb and resource. Distinguishes from sibling tools like 'translate' and 'list_languages'.

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

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

No guidance on when to use this tool versus alternatives like 'translate' or 'list_languages'. No prerequisites or limitations mentioned.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, indicating safe, idempotent, non-destructive behavior. The description adds that results are 'ready to call directly, no second schema lookup needed,' and specifies default/max limit. No contradictions.

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

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

The description is front-loaded with the main purpose and usage directive. It lists many example domains, which is helpful but slightly verbose. Every sentence adds value, and it is well-structured.

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

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

Given no output schema, the description explains that the tool returns 'top-N most relevant tools with names, descriptions, and full input schemas (with curated examples).' It covers input parameters, behavior, and output content adequately for an agent to use it effectively.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining that 'query' accepts aliases (task, q, description, search) and provides example values, clarifying usage beyond the schema's individual field 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: 'Find tools by describing the data or task.' It distinguishes from siblings by being the discovery meta-tool, while siblings are specific data tools. Returns ready-to-call tool definitions with schemas, making it unique.

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 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' Provides when-to-use context. However, it doesn't explicitly state when not to use (e.g., if you already know the tool).

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

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

Annotations already indicate read-only, idempotent, non-destructive. Description adds context about USPTO API sunset and soft-fail, parallel fan-out behavior, and data sources. No contradiction with annotations.

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

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

Description is detailed and includes examples, but is slightly lengthy. However, it is well-structured with clear sections and front-loaded key information, making it easy to parse.

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, fallbacks, and limitations, the description is very complete. It explains output fields, API constraints, and fallback behavior. No output schema, but return values are well described.

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

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

Schema has 100% coverage, but description adds meaningful context: explains type enum only supports 'company', value can be ticker or zero-padded CIK, and explicitly states names not supported. This goes beyond the schema descriptions.

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

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

The description clearly states the tool provides a full cross-source profile of a US public company in one parallel call, listing specific data sources and outputs. It distinguishes from chaining multiple single-source 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 lists example queries ('Tell me about X', 'research Acme') and provides when-not-to-use guidance: names not supported, advises using resolve_entity first. Strongly prefers this tool over chaining alternatives.

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

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

Annotations already indicate destructiveHint=true and idempotentHint=true. The description adds behavioral context about clearing sensitive data and stale context, enhancing transparency beyond annotations.

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

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

The description is two sentences plus a pairing instruction, highly concise and front-loaded with the essential action.

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

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

For a simple deletion tool with one parameter, good annotations, and no output schema, the description provides complete context including when to use and results.

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

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

With only one parameter (key) and 100% schema description coverage, the description adds no additional meaning beyond 'Memory key to delete'. 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 'Delete a previously stored memory by key', using a specific verb and resource. It distinguishes itself from siblings like '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 provides use cases: 'when context is stale, the task is done, or you want to clear sensitive data'. It also suggests pairing with 'remember' and 'recall', offering clear guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, establishing a safe, non-mutating profile. The description adds that the tool fetches the page and extracts data, which aligns but offers little extra behavioral context beyond the annotations.

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

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

The description is three sentences plus a use-case list, efficiently front-loading the core purpose and output. It avoids redundancy, though the use-case list could be integrated more concisely. Still, it earns its length.

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

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

For a simple, read-only tool with two parameters and no output schema, the description covers the main functionality, output format, and use cases. No significant gaps are apparent given the annotations cover safety and idempotency.

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

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

Schema coverage is 100% with both parameters (url and max_links) described. The tool description mentions fetching pages and extracting links, which indirectly relates to the parameters but does not add explicit meaning beyond what the schema already provides. Baseline 3 applies.

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

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

The description clearly states the tool generates a production-ready llms.txt file for any URL, specifically for AI crawlers. It distinguishes itself from sibling tools like ai_visibility_check and scan_competitor_ai_presence by focusing on file generation rather than checking or scanning.

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

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

The description lists three explicit use cases (getting a site indexed, drafting for own project, auditing competitor), providing clear context for when to use. It does not mention when not to use or compare directly to alternatives, but the context is sufficient for an agent to decide.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds no additional behavioral context beyond restating the action.

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?

One concise sentence that immediately conveys purpose. No extraneous information. Perfectly 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?

Complete for a simple list tool with no parameters, comprehensive annotations, and an output schema. All necessary context is present.

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

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

With zero parameters, the baseline is 4. The description adds no parameter info, but none is needed. Schema coverage is 100%.

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

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

The description clearly states the tool lists languages supported by a specific service (LibreTranslate instance), distinguishing it from sibling tools like detect_language (detection) and translate (translation).

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

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

No explicit when-to-use or alternatives are given, but the description implies use for retrieving available languages before translation or detection. Lacks guidance on when not to use it.

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

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

Annotations already declare readOnly=true, destructive=false, idempotent=true. Description adds return field details but no additional behavioral traits beyond annotations.

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

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

Two concise sentences with no wasted words. All information is front-loaded.

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

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

No output schema exists, but description lists all returned fields. Given simplicity and annotations, description is complete enough.

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 no extra meaning beyond the schema parameter description for include_inactive.

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 verb 'list', resource 'subscriptions', and scope 'caller's active'. Distinguishes from sibling tools like subscribe/unsubscribe.

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

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

Explicitly states when to use: to review subscriptions before adding more or to find an id to cancel. No explicit when-not, but sufficient 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?

Beyond annotations, it discloses rate limiting (5 per identifier per day), that it doesn't count against tool-call quota, and that the team reads digests daily. 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 well-structured sentences that front-load the purpose, then provide usage guidelines and constraints. Every sentence earns its place with no redundancy.

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

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

For a feedback tool, the description covers what, when, how, and constraints. No output schema needed; the return is likely a confirmation. Context is complete for an AI agent.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by elaborating on the 'type' enum and providing context for the 'message' field, enhancing understanding beyond schema alone.

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

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

The description clearly states the tool's purpose: to provide feedback about bugs, missing features, data gaps, or praise. It distinguishes from sibling tools by focusing on feedback rather than querying or data retrieval.

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 on when to use the tool for each feedback type (bug, feature/data_gap, praise) and instructions on how to format the message. Also states rate limits and that it's free.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable context: it's self-aggregating, derived from CF analytics-engine, no PII, and cached 5min-1h. 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 concise with no wasted sentences. It starts with the main purpose, lists use cases in a clear format, and ends with technical details. Each 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 low tool complexity (one param, no output schema), the description sufficiently explains output (top tools, top packs, total call volume) and data freshness. It doesn't detail exact response structure, but clarity is adequate.

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

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

Schema coverage is 100% with one parameter. The description adds meaning beyond schema by explaining that shorter windows surface hot trends and longer windows show steady-state demand, which helps in parameter selection.

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 returns top tools, top packs, and total call volume over a recent window. It uses specific verbs and resources, and distinguishes from sibling tools by focusing on trending data rather than querying or searching.

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

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

The description provides three explicit use cases (discovering hot data, confirming canonical tools, aligning use cases). While it doesn't explicitly name alternatives or state when not to use, the use cases give clear guidance on appropriate contexts.

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 significant behavioral details: walks child markets, checks ordering, computes partition check, enforces Jaccard similarity ≥0.30, removes placeholder slugs, and returns null if placeholder fraction >20%. 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 verbose but well-structured with bold headings and clear separation of modes. Every sentence adds value, though some sections could be slightly condensed. It is front-loaded with the requirement, aiding quick comprehension.

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

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

Despite lacking an output schema, the description explains the response structure (opportunities[], partition_check). It covers edge cases like placeholder filtering and similarity thresholds. For a complex tool with two modes, the description is comprehensive and leaves no major gaps.

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

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

Schema coverage is 100% with descriptions for both parameters. The description elaborates beyond schema by explaining the semantics of each mode, providing examples of slugs, and detailing the behavior of 'event' and 'topic' parameters. This adds substantial meaning.

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

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

The description clearly states the tool finds arbitrage opportunities via monotonicity violations and partition-sum checks. It distinguishes between two modes (event and topic), providing a specific verb and resource. While it doesn't explicitly contrast with siblings like 'polymarket_edges', the purpose is well-defined and unambiguous.

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

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

Explicitly states that one of 'event' or 'topic' is required, and provides recommendations: use 'event' for a specific market, 'topic' for cross-event scanning. This guides the AI agent on when to use each mode, fulfilling the usage guidelines dimension perfectly.

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

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

Annotations already mark the tool as readOnly, openWorld, idempotent, and non-destructive. The description adds substantial context: caching (1h KV), details on model families, edge calculation, slippage handling, and diagnostic output. 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 comprehensive but verbose, with dense paragraphs. It is structured with clear section headers, but could be more concise by grouping related details. Every sentence adds value, but the length may overwhelm agents.

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 structure (by_segment, fed_candidates, _diagnostics), why segments may be empty, and the role of knobs. This is 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%, with all 9 parameters described. The description adds value by explaining parameter interactions (e.g., min_partition_leg_kelly vs min_kelly) and usage context (e.g., slippage_pp defaults). This enriches understanding beyond the schema.

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

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

The description clearly states the tool's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It distinguishes itself from sibling tools like polymarket_arbitrage by focusing on Pipeworx data-driven edges for daily betting opportunities.

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 'Built for "what should I bet on today" agents,' indicating primary use case. It explains the three segments and how to use knobs like min_liquidity and max_spread_pp. However, it does not explicitly state when not to use this tool versus alternatives like bet_research or polymarket_arbitrage.

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

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

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds substantial behavioral context: it uses snapshots, decay is computed from daily closes of edge_pp_net, gaps exist when no scan occurred, and the response includes both tracked and expired opportunities. This complements the annotations 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 detailed but not verbose. It front-loads the key question and then explains args and response structure. Every sentence adds value. It could be slightly shortened, but the complexity of the tool warrants this level of detail.

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

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

Despite having no output schema, the description fully describes the response structure: 'tracked[]' with 'edge_pp_net' time-series, 'first_seen', 'trend', 'decay_pp_per_day'; 'expired[]' with 'lifespan_days'; and 'snapshot_dates[]'. It also explains limits and data gaps. For a tool with 2 parameters and no nested objects, this is completely adequate.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaning by clarifying that 'days' is a lookback with default 14 and max 30, and 'window' refers to a snapshot family with default '1wk'. This extra context about defaults and the concept of snapshot families improves understanding beyond the schema.

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

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

The description clearly states the tool's purpose: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots.' It answers a specific question: 'how long has this edge existed and is it shrinking?' This distinguishes it from the sibling tool 'polymarket_edges' by focusing on historical trends rather than current snapshots.

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

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

The description provides strong context for when to use this tool: to differentiate between fresh and old wide edges, implying it's for historical analysis rather than current edge data. It also mentions limitations (60-day snapshot TTL, snapshot dependency). However, it does not explicitly contrast with siblings like 'polymarket_edges' or 'polymarket_arbitrage', leaving that implicit.

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 valuable context: it 'walks the ladder', returns verdicts (clean|degraded|cannot_fill), and highlights forced_directional_risk. This goes beyond annotations but doesn't require full behavioral detail since annotations cover safety.

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 uppercase headings for modes and clear separation. It front-loads the main purpose. However, some redundancy exists (e.g., listing return fields in both prose and later in detail). 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?

No output schema is provided, so the description fully covers return fields for both modes (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict for single-market; theoretical_sum, realizable_sum, capture_ratio, profit_usd, per-leg detail, thin_legs, max_clean_notional_usd, forced_directional_risk for basket). It also explains when to use and the risks, making it complete for an agent to invoke correctly.

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

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

Schema coverage is 100% with descriptions already present. The description adds meaning by explaining the difference between single-market (slug/URL + side) and basket (event slug/URL) modes, the default side behavior (auto from partition sum), and interpretation of size_usd (max spend vs. settlement notional). This adds value beyond the schema.

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

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

The description clearly states it performs a 'realizable-vs-theoretical edge check against live CLOB order-book depth' and distinguishes between single-market and basket modes. It differentiates from sibling tools like polymarket_arbitrage and polymarket_edges by focusing on fill risk rather than signal generation.

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 instructs 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500' and warns against partial fills converting arb to directional positions. Provides clear context for applicability.

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=true, etc.), description adds extensive behavioral context: response structure, safety fields (compatibility_warning, temporal_alignment, skipped_cross counters), and explains implications of mismatched bet shapes or temporal gaps. No contradiction with annotations.

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

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

Front-loaded with core purpose in first sentence. Structured logically: modes, response format, safety fields. Some redundancy (e.g., mode explanations in both description and parameter descriptions), but overall efficient given complexity.

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

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

No output schema, yet description fully covers return values (leg prices, spreads, safety fields) and all parameters. Includes real-world caveats about rarity of tradeable spreads. Comprehensive for a tool with 3 parameters and two modes.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the two modes, listing the 10 topic shortcuts explicitly, and clarifying that explicit parameters override topic-mapped sides. This goes slightly beyond the schema, earning a 4.

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

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

The description clearly states the tool computes cross-venue spreads between Kalshi and Polymarket for the same resolving question, with two distinct modes (topic shortcuts and explicit tickers). It differentiates from sibling tools like polymarket_arbitrage by specifying the cross-venue 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?

Explicit guidance on when to use each mode, including warnings that most topic shortcuts currently return compatibility warnings and are not tradeable. Also explains temporal alignment requirement and equivalence of bet shapes, providing clear when-not-to-use criteria.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds value by explaining scoping (by identifier) and the pairing pattern with remember/forget, but does not contradict annotations.

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

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

Two sentences with zero waste. Front-loaded with the primary action, then secondary usage, then context. Every sentence adds 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?

For a simple read-only tool with rich annotations and no output schema, the description covers all necessary aspects: what it does, when to use it, how to use it, and its scope. No gaps for an agent to select and invoke correctly.

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

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

Schema coverage is 100% (key parameter fully described). The description adds meaning by explaining the purpose of the key (to retrieve that specific value) and the behavior when omitted (list all keys). This aligns with the baseline 3 for high coverage.

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

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

The description uses specific verbs ('Retrieve', 'list') and clearly identifies the resource (saved memory via remember). It distinguishes from siblings by naming remember (save) and forget (delete) as counterparts, and explains the scoping mechanism (by identifier).

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: to look up context stored earlier, and contrasts with re-deriving from scratch. Provides guidance on omitting the key to list all keys. Pairing with remember and forget gives clear alternatives.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds behavioral details such as returned fields (source, citation_uri, raw payload) and the mark_read parameter's effect on future calls, which are not captured 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 (4 sentences) and front-loaded with the main purpose. Every sentence adds value without redundancy, maintaining a clear and efficient structure.

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

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

Given no output schema and 5 parameters with 100% schema coverage, the description provides sufficient context: what is returned, filtering options, polling suitability, and mark_read behavior. It is complete for effective use.

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

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

Schema coverage is 100% with descriptions for each parameter. The description adds examples (e.g., 'sec_8k' for type) and clarifies the mark_read behavior, but these are marginal improvements over the schema descriptions. 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 verb 'pull' and the resource 'fired events from your subscription feed'. It specifies what the tool returns (alerts with source, citation_uri, raw payload), making the purpose unambiguous and actionable.

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

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

The description provides context on when to use this tool for polling and mentions an alternative endpoint for scripts and dashboards. However, it does not explicitly state when not to use this tool compared to siblings, which could be improved.

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

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

The description adds substantial behavioral details beyond annotations: it fans out in parallel, has fallback logic (GDELT→GNews), and notes a soft-fail for USPTO. Annotations already indicate readOnly, openWorld, idempotent, and non-destructive, so the description complements well.

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

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

The description is a single dense paragraph that is efficient but could benefit from slight structuring for readability. It front-loads query examples, which helps with quick scanning.

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 return structure (grouped by source, total_changes, citation URIs) and covers each source's behavior. All parameters are documented, and the tool's complex behavior is fully described.

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

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

With 100% schema coverage, baseline is 3, but the description significantly enhances parameter understanding: explains `since` formats with examples, clarifies `value` can be ticker or CIK, and recommends typical values like '30d'.

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 provides a change feed for a company over a time window, listing specific sources (SEC EDGAR, GDELT→GNews, USPTO) and distinguishing itself from the sibling tool 'entity_profile' for static profiles.

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

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

The description gives explicit examples of when to use (e.g., 'What's new with X') and directly tells when to use entity_profile instead. It does not explicitly state when not to use, but the alternative 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 discloses persistence behavior (authenticated users persistent, anonymous 24 hours), scoping by identifier, and that it stores key-value pairs. Annotations are consistent: readOnlyHint=false implies writing, destructiveHint=false matches description, idempotentHint=true aligns with repeated saves being fine.

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

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

The description is a single paragraph but efficiently covers purpose, usage, and technical details. It is front-loaded with the main action. One minor point: it could be slightly more structured with bullet points, but it is concise and clear.

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

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

Given the tool's simplicity (2 parameters, no output schema) and the rich annotations, the description is complete. It explains when to use, how storage works, retention policy, and how it relates to siblings recall and forget.

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

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

Schema has 100% coverage with descriptions for key and value. The description adds context about key-value pairing and examples in the key schema description. However, it does not add significant new meaning beyond the schema, so 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's purpose: 'Save data the agent will need to reuse later' across conversation or sessions. It specifies the verb (save), resource (data as key-value pairs), and distinguishes from siblings recall and forget.

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

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

The description provides explicit when-to-use guidance: 'Use when you discover something worth carrying forward (a resolved ticker, a target address, a user preference, a research subject)'. It also mentions pairing with recall and forget, offering 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 mark readOnlyHint and idempotentHint. The description adds behavioral details like internal cascading lookups, auto-disambiguation, and citation URIs, but omits rate limits or error handling.

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 clearly structured by type. It is informative but slightly lengthy; 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?

Without an output schema, the description adequately covers return values (ticker, CIK, RxCUI, URIs) and input formats. Missing error handling details but sufficient for a lookup 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?

With 100% schema coverage, the description enhances parameter meaning by explaining return values per type and input examples (e.g., 'AAPL', 'ozempic'), adding value beyond schema.

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

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

The description explicitly states the tool resolves names to canonical identifiers, provides example queries, and distinguishes between supported types (company, drug). It clearly differentiates from siblings by stating 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?

The description advises 'Use FIRST whenever you have a name but need an ID,' providing clear context. It does not explicitly state when not to use it, but the sibling list implies alternatives.

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

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

Annotations already indicate readOnly, openWorld, idempotent, non-destructive. The description adds valuable behavioral details: calls ai_visibility_check multiple times, ranks by score, returns ranked list with score/confidence/signal density per entity. 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 plus a parenthetical. Front-loaded with main purpose, then method and use case. No fluff, every sentence adds value. Properly structured.

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

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

The description covers the return format (ranked list with score, confidence, signal density), explains the tool calls another tool, and provides a use case. With no output schema and all parameters documented in schema, it is largely complete. Minor gap: does not mention potential costs or rate limits of multiple probes.

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 parameters are already well-documented. The description provides no additional parameter-specific semantics beyond what the schema offers (e.g., 'context' is optional shared context). The mention of 'first entity treated as subject' is a usage note, not parameter semantics.

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

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

The description clearly states the tool's purpose: 'Compare AI visibility across multiple entities side-by-side.' It specifies the verb (compare/scan), resource (AI visibility of entities), and method (probes with ai_visibility_check, ranks by score). It distinguishes from sibling tools like ai_visibility_check (single entity) and compare_entities (general comparison).

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

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

The description provides clear context: 'Useful for competitive AI-marketing audits' and gives an example. It notes the first entity is treated as subject for narrative. However, it does not explicitly state when not to use this tool or mention alternatives like ai_visibility_check for single entity checks.

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

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

Annotations already indicate readOnly, idempotent, non-destructive. Description adds details on external sources, partial failures (bundlephobia timeout), graceful degradation, and that sources_failed will list issues. No contradiction.

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

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

Description is long but front-loaded with purpose. Each sentence adds value, though some details (e.g., partial failure specifics) could be slightly more concise. Generally well-structured.

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

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

Despite no output schema, the description lists return fields (summary block, per-advisory detail, links, alternative versions) and covers edge cases (partial failures, measurement delay). Complete for a composite 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 has 100% coverage with clear descriptions. Description adds minimal extra value, noting scoped packages are accepted and version defaults to latest. Baseline 3 is appropriate as schema does the heavy lifting.

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

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

The description clearly states it is a composite check for npm packages, covering license, advisories, version history, and bundle size from multiple sources. It distinguishes from siblings by being a one-call solution for questions about safety, popularity, and size.

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" or "what does adding lodash cost me"'. Also specifies ecosystem limitations (NPM only in v1) and alternatives 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. Description adds embedding model (BGE-base-en), similarity metric (cosine), window size (500-char overlapping), character cap (200K with truncation flag), and return format (passages with offsets and scores). No contradiction.

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

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

Three dense sentences front-loaded with purpose. Every sentence adds value: what it does, when to use, how it works, return details. 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?

No output schema, but description covers return values (passages with offsets and similarity scores), pairing with sibling, and behavior on truncation. Provides complete guidance for a retrieval tool.

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

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

Schema coverage is 100% with descriptions for text, query, and limit. The description adds context: text as 'document text', query with natural-language examples, limit as max passages. Also explains mechanics (overlapping windows) enhancing semantics beyond schema.

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

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

The description clearly states it performs 'semantic search INSIDE a fetched record', specifying the verb 'search' and the resource 'fetched record'. It distinguishes itself from siblings like ask_pipeworx_grounded by explaining the pairing and contrasting with fetching 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 when the record is too big to cram into the prompt' and implies not to use for fetching. Provides alternative pairing with ask_pipeworx_grounded for grounding.

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 mutability, idempotency, and non-destructiveness. The description adds crucial details: returns subscription id, delivery limitations (SMS cap, webhook auto-disable after 10 failures), and signing secret info. 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 thorough but somewhat lengthy. It front-loads the main purpose and uses bullet points in a structured way, though a bit verbose.

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

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

No output schema, but the description states 'Returns the new subscription id'. It covers prerequisites, types, delivery channels, and limitations, making it fully informative.

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

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

With 100% schema coverage, the description adds meaning by providing concrete examples for each type and delivery option, making the tool easier to use.

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 'Create a proactive monitoring subscription to a live-data event stream' and distinguishes it from sibling tools like 'unsubscribe' 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?

It specifies when to use (need to subscribe) and prerequisites (Pipeworx OAuth account), but doesn't explicitly mention when not to use or compare with alternatives like 'recent_alerts'.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds that it returns category-bucketed example questions from a live catalog and accepts optional topic filtering. No contradictions.

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

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

The description is front-loaded with trigger phrases and provides all necessary information in a structured manner. Slightly verbose but every sentence adds value.

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

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

Given the onboarding purpose and lack of output schema, the description covers purpose, usage, behavior, parameter details, and context. It is sufficiently complete for an agent to use correctly.

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

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

Schema coverage is 100%, but the description adds meaning by specifying the optional nature of topic, listing allowed values (finance, pharma, etc.), and explaining the effect of omission (cross-category spread).

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 onboarding, answering 'what can I ask?' with example questions and tool+argument shapes. It distinguishes from discover_tools by focusing on question suggestions rather than tool listing.

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 suggests using this tool FIRST when unsure of Pipeworx capabilities. Mentions optional topic parameter for focus. Does not list explicit exclusions or alternatives but provides clear 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=true, idempotentHint=true, so the description does not need to repeat safety. It adds context about return values (translated text and detected source), which is useful but not extensive.

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

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

The description is two sentences with no wasted words. It front-loads the primary action and adds key details efficiently.

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 4 parameters (2 required) and that output schema exists, the description covers the main purpose and return values. It does not explicitly mention the 'format' parameter, but that is detailed in the schema.

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

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

Schema coverage is 100%, so baseline is 3. The description mentions that source can be 'auto', which is already in the schema's default. No additional meaning beyond schema is added.

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 'translate' and the resource 'text', and mentions auto-detection and return values. It distinguishes from sibling 'detect_language' by implying translation includes detection but not as a separate function.

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

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

The description implies usage by stating source can be 'auto' for auto-detect, but it does not explicitly guide when to use this tool vs the separate 'detect_language' sibling. No exclusions or alternatives are mentioned.

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

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

Discloses that the row is deactivated (not deleted) and that historical events remain accessible via recent_alerts. This adds valuable context beyond annotations (readOnlyHint, destructiveHint, idempotentHint), fully informing the agent of the tool's behavior.

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

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

Two sentences, no redundant information, front-loaded with the core action and key constraint. Every sentence adds value.

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

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

Given the tool's simplicity (one required param, no output schema), the description covers the essential behavioral details (ownership, deactivation, historical impact). Nothing important is missing.

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

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

Schema description coverage is 100% and the parameter 'id' is well-documented in the schema. The description does not add additional semantic information beyond what the schema provides, meeting the baseline expectation.

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 action ('Cancel a subscription by id') and resource (subscription). Differentiates from siblings like 'subscribe' and 'list_subscriptions' by emphasizing ownership enforcement.

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 ownership constraint ('you can only cancel your own subscriptions'), indicating when the tool is applicable. Does not mention alternatives or exclusions beyond ownership, but the context is clear.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds behavioral context: it returns a verdict with five possible values, extracted structured form, actual value with a pipeworx:// citation, and percent delta. It also mentions that it replaces multiple sequential calls, which is useful for understanding overhead.

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 example queries, then the purpose, domain, and output. It is not overly verbose but includes necessary details. A few sentences could be tightened, but overall it is well-structured and each sentence adds value.

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

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

Given no output schema, the description fully explains the return value: a verdict, structured form, actual value with citation, and percent delta. It also mentions the domain scope and that it replaces multiple calls. For a single-parameter tool, this is complete and sufficient for an agent to decide when to use it.

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

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

Schema coverage is 100% for the single 'claim' parameter, so the schema already documents it thoroughly. The description provides example claims and emphasizes natural language, but does not add significant meaning beyond that. Baseline 3 is appropriate since the schema covers the parameter well.

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: natural-language claim verification against authoritative sources. It provides example queries and explicitly says it checks whether something a user said is factually correct. It distinguishes itself from sibling tools by focusing on financial claims via SEC EDGAR + XBRL, making its resource and action specific.

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

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

The description explicitly states when to use the tool: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also specifies the current domain (company-financial claims) and lists the types of claims supported (revenue, net income, cash position). However, it does not explicitly mention when not to use it or suggest alternatives for non-financial claims, which would improve the score to 5.

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