videogames

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

Annotations indicate readOnly, idempotent, non-destructive. The description adds beyond that by explaining return format (per-model score, confidence, signals, raw_response + combined view), cost implications (free default, BYO key), and that the key is passed directly to Anthropic. 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 3-4 sentences, front-loaded with the core action, and every sentence adds value (purpose, model options, return format, use cases). No fluff or repetition.

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

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

Given 4 parameters and no output schema, the description covers the return format, use cases, and model options. It could mention error handling (e.g., invalid API key) but is otherwise comprehensive for the tool's complexity.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the default model, how the _apiKey works, and the role of context for disambiguation. This provides meaning beyond what the schema descriptions alone offer.

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

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

The description clearly states the tool probes LLMs for knowledge about an entity and scores visibility (0-100). It distinguishes from siblings by specifying 'AI-marketing audits' and 'competitive monitoring', and the verb 'Probe' with 'score visibility' is specific 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 explains when to use (AI-marketing audits, pre-launch brand checks, competitive monitoring) and how to invoke with a default model or BYO Anthropic key. It does not explicitly mention when not to use or differentiate from 'scan_competitor_ai_presence', 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?

Description adds value beyond annotations by mentioning structured answers with citation URIs and routing across many sources. No contradiction with annotations (readOnlyHint, etc.).

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

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

Single paragraph with front-loaded directive and concrete examples. Every sentence adds value, though could be slightly more 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?

Covers main purpose and usage, but missing limitations, error handling, or behavior for out-of-scope questions. With no output schema, return format details would further help.

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 aliases described. Description provides natural language usage examples and clarifies the question parameter, adding 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 answers factual questions with authoritative structured data and citations. Verb 'ask' and resource 'Pipeworx' are clear, but no explicit differentiation from sibling tools like 'ask_pipeworx_grounded' or 'deep_research'.

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

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

Explicitly says 'PREFER OVER WEB SEARCH' and lists example queries and data types. Provides clear when-to-use context with trigger phrases, but does not specify when not to use or alternatives.

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

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

Annotations already indicate safe read operation; description adds critical behavioral details: costs one extra LLM call, returns structured refusal reasons, and extracts answers only from tool results. No contradiction with annotations.

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

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

Dense yet efficient; front-loaded purpose, then detailed process and usage notes, every sentence adds value without redundancy.

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

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

Despite no output schema, description fully specifies return structure including fields and refusal reasons, and differentiates from 32 sibling tools 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% with clear descriptions for all parameters including aliases. Description reinforces that question accepts multiple aliases, adding clarity beyond the schema.

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

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

Description clearly states it is a 'hallucination-resistant answer mode' for high-stakes reads, explains the routing and extraction process, and distinguishes from the sibling 'ask_pipeworx' by highlighting the additional 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 tells when to use ('when an answer will be quoted, cited, or acted on') and when not to ('prefer ask_pipeworx for casual lookups'), providing clear guidance for selection.

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

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

The description extensively discloses behavioral traits beyond annotations, including classifiers, fan-out examples, resolver contract, parent event extraction, news fallback handling, safety checks for low-confidence matches, closed markets, wide spreads, and cancellation rule parsing. No annotation 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 very long and detailed, containing multiple paragraphs and examples. It is structured with section-like labels (e.g., CLASSIFIERS, FAN-OUT EXAMPLES) and front-loaded with core purpose, but could be more concise for agent consumption.

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

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

No output schema exists, so the description must explain return values. It thoroughly describes result fields (market, analysis, evidence, match_confidence, parent_event, news, cancellation_rule) and edge cases. Covers safety, fallback, and resolution risks comprehensively.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaningful context for each parameter: examples of market input, explanation of depth levels, and effect of include_raw. 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 researches a Polymarket bet by pulling Pipeworx data in one call, and specifies accepted input types (slug, URL, question text). It distinguishes from sibling tools like polymarket_arbitrage and polymarket_edges, which are more specialized.

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 suggests using for 'should I bet on X', 'what does the data say about Y', or 'is there edge in Z', but does not explicitly state when not to use it or mention alternative tools. Usage is implied rather than explicitly guided with exclusions.

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

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

The description adds significant behavioral context beyond the annotations: it details the data returned (paired data with citation URIs), sorting by primary metric, handling of off-calendar fiscal years, and efficiency (replaces 8-15 lookups). It fully aligns with the annotations (readOnlyHint, idempotentHint, etc.) and provides rich detail for agent decision-making.

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

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

The description is relatively dense but well-structured: front-loaded with example phrases and key guidance, then details on data sources and behavior. Every sentence contributes value, though it could be slightly more concise. Overall, it is well-organized and not verbose.

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

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

Despite no output schema, the description thoroughly explains the return format (paired data, citation URIs), sorting, and what data each type returns. It also addresses edge cases like off-calendar fiscal years and gives performance context. This makes the description complete for an agent to understand and invoke the tool correctly.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaningful context: it explains what each 'type' value does (company pulls latest 10-K metrics, drug pulls FAERS/FDA/trial counts) and provides examples of valid inputs (e.g., tickers for company, drug names). This extra semantic information raises the score above 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 it performs side-by-side comparison of 2-5 companies or drugs, specifying data sources (SEC EDGAR for companies, FAERS/FDA/trials for drugs). It includes example queries like 'compare X and Y' and explicitly distinguishes from sibling tools by stating 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' This meets the criteria for specific verb+resource and sibling differentiation.

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

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

The description provides clear guidance on when to use the tool (when comparing entities, given example queries) and explicitly states to prefer it over sequential lookups. However, it does not explicitly mention when not to use it or alternative tools for other tasks, so it falls short of a 5.

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

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

Annotations already declare read-only, idempotent, not destructive. The description adds context about account requirement, pricing for depth:thorough, the internal parallel decomposition, output format with gaps[], expected duration, and that it is not open-web search. No contradiction with annotations.

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

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

The description is long but well-structured, starting with the critical account requirement and alternative, then explaining the tool's mechanism and use cases. Every sentence adds value, though slightly verbose for a concise standard.

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

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

Despite no output schema, the description fully explains the output format (findings packet with evidence, confidence, source, timestamp, gaps). It also covers expected wait time, account requirements, and when to expect empty results. Complete for a complex tool.

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

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

Schema coverage is 100% and both parameters (question, depth) are described in the schema. The description mentions depth in the context of account requirement but does not add significant extra meaning 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 it performs multi-source research across structured data sources, decomposes questions into facets, and returns findings with citations and gaps. It distinguishes itself from open-web search and from the sibling tool ask_pipeworx.

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

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

Explicitly says when to use (broad/multi-part questions over structured data) and when not to (single lookup, breaking news), with alternative tools named (ask_pipeworx). Also notes account requirement and free/paid tiers.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description further explains the return format (top-N relevant tools with full schemas and examples ready to call) and the query parameter's flexibility (multiple aliases). 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 purpose and includes a bullet of data domains. While clear and well-organized, a few redundant phrases ('look up, or discover') could be trimmed. Still, very effective.

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

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

For a discovery tool with no output schema, the description covers return content (names, descriptions, full schemas with examples) and emphasizes readiness for direct invocation. No missing critical context.

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

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

100% schema coverage with each parameter described. The description adds value by noting aliases for 'query' (task, q, description, search) and providing two concrete examples in the schema. This goes beyond the basic schema definitions.

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

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

The description clearly states the tool's purpose: 'Find tools by describing the data or task.' It lists many specific data domains (SEC filings, FDA drugs, etc.) and distinguishes itself from sibling tools by being the primary discovery tool for browsing available capabilities.

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

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

Explicitly advises 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' Also specifies use cases like browsing, searching, and discovering tools for specific data types, leaving no ambiguity.

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

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

Annotations indicate read-only, idempotent, open-world. Description adds behavioral details: fans out across multiple sources, parallel calls, soft-fail for patents, and required input format. No contradictions.

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

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

The description is somewhat long but every sentence adds value. It is front-loaded with examples and structured logically. Slightly verbose but still efficient.

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

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

No output schema, but description fully details all returned fields (cik, filings, fundamentals, patents, news, LEI) and limitations. Complete for the tool's complexity.

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

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

Schema coverage is 100%. Description adds meaning beyond schema: value can be ticker or CIK, names not supported, type is only 'company'.

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

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

The description starts with clear example queries and explicitly states it returns a full cross-source profile of a US public company in one parallel call, listing data sources and returned fields. It distinguishes from sibling tools like resolve_entity by noting names are not supported.

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

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

Explicitly says 'ALWAYS PREFER over chaining' for holistic views and instructs to use resolve_entity first if only a name is available. Provides clear when-to-use and when-not-to-use guidance.

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

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

The annotations already declare the tool as read-only, idempotent, open-world, and non-destructive. The description does not add any behavioral traits beyond what annotations provide, but it is consistent and adds context about the return fields. No additional traits like rate limits or auth are mentioned, which are not critical here.

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

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

The description is two sentences, front-loading the key action and return fields. Every word is useful, with no redundancy or filler. It is appropriately sized for the tool's complexity.

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

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

Given the existence of an output schema, the description does not need to detail return values. It covers the filtering method, constraints (free-to-play), and a summary of return fields. No gaps are evident for this simple filter tool.

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

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

Schema coverage is 100%, so the schema already describes both parameters well. The description adds the context that the filter is for 'free-to-play games' but does not significantly enhance parameter semantics beyond providing an example in the description itself. Baseline of 3 is appropriate.

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

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

The description clearly states the verb 'filter', the resource 'free-to-play games', and the method 'by tag (dot-separated combination of attributes)'. It lists the return fields, distinguishing it from sibling tools like 'list_games' (which lists all) and 'get_game' (which retrieves a single game).

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

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

The description implies usage for filtering games by a specific tag combination, which is clear. However, it does not explicitly state when to use this tool versus alternatives (e.g., 'get_game' for a single game, 'list_games' for all). The examples in the input schema provide some guidance but no explicit when-not-to-use instructions.

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

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

Annotations already provide destructiveHint=true. The description confirms deletion without adding new behavioral details. No contradiction, but no extra value beyond annotations.

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

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

Two sentences, no fluff. Action verb first, then usage context. Efficient 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?

Given the tool's simplicity (1 param, no output schema) and rich annotations, the description is fully adequate. No gaps.

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

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

Only one parameter 'key' with schema description 'Memory key to delete'. Schema coverage is 100%, so description adds no further meaning beyond the schema.

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

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

The description clearly states 'Delete a previously stored memory by key', which is a specific verb and resource. It distinguishes 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?

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

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 details the tool's behavior—fetching the page, extracting title/description/key links, emitting standard markdown—beyond the annotations. Annotations already indicate read-only, idempotent, non-destructive behavior, and the description adds process and output specifics 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 four sentences, front-loading the main purpose. Each sentence adds value: purpose, process, output format, use cases. No wasted words.

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

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

For a simple tool with no output schema, the description covers purpose, process, output format, and use cases. It could mention potential error cases (e.g., fetching fails) but is otherwise complete given the annotations.

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

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

Schema coverage is 100%, and the description adds little beyond the schema for the two parameters. It mentions the output as a 'single text blob' but does not elaborate on the parameters themselves; the schema already describes url and max_links 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 uses a specific verb ('Generate') and resource ('llms.txt file') and clearly distinguishes from sibling tools like ai_visibility_check or scan_competitor_ai_presence by focusing on generating the standard file format.

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: 'getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.' This provides clear context and excludes 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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description's mention of returning detailed game info adds marginal behavioral context. 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?

Single sentence with front-loaded verb 'Get full details'. Efficiently lists all returned fields 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?

Tool has one required parameter, and the description explicitly states all returned fields. Output schema exists, so return structure is fully documented. Complete for a single-game 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?

Schema coverage is 100% with an example and description. The description repeats 'by its FreeToGame ID', adding no new meaning beyond the schema's parameter description and examples.

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

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

Description clearly states it retrieves full details for a specific free-to-play game by its FreeToGame ID, listing the exact fields returned. This distinguishes it from sibling tools like 'list_games' and 'filter_games'.

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 use when you have a specific game ID, but does not explicitly state when not to use it or mention alternatives. Sibling context provides differentiation, but no explicit guidance is given.

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

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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint. The description adds that it returns specific fields but does not disclose pagination, rate limits, or authentication needs. No contradiction with annotations.

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

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

Two concise sentences: first states the core action with optional filters and sorting, second lists returned fields. No wasted words, front-loaded with purpose.

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

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

With an output schema present and clear annotations, the description adequately covers the tool's behavior and output. It could mention result limits or pagination for completeness, but overall it is sufficient.

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

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

Schema description coverage is 100%, so baseline is 3. The description summarizes parameters (platform, category, sort) but does not add new meaning beyond what the schema already provides for each parameter.

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

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

The description clearly states the tool lists free-to-play games from a specific source (FreeToGame) with optional filters and sorting. It distinguishes from siblings like 'get_game' (single game) and 'filter_games' (likely more advanced filtering) by its broad listing nature.

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

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

No guidance on when to use this tool vs. siblings like 'filter_games' or 'get_game'. The description only explains what it does, not when it is appropriate or when to avoid 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 the tool safe and idempotent. The description adds detail: returns specific fields, lists caller's own subscriptions, and explains the include_inactive parameter.

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

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

Two sentences, front-loaded with action and output, followed by usage advice. No redundant words.

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

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

For a simple listing tool with one optional parameter and rich annotations, the description covers purpose, output fields, and usage context completely.

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

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

Schema coverage is 100% with a clear description for the only parameter. The description reinforces the default active-only behavior but adds no new syntax or format details beyond the schema.

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

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

The description clearly states the tool lists active subscriptions and enumerates return fields. It distinguishes from subscription management siblings like subscribe and unsubscribe.

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

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

The description explicitly guides the agent to use this tool to review monitored subscriptions before adding more or to find an id to cancel, providing 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?

Discloses rate limit of 5 per identifier per day, free usage, no quota impact, and that team reads digests daily. Adds 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?

Four sentences, front-loaded with main purpose, no filler. Efficient and clear.

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

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

Covers all aspects: what to send, when to use, constraints, and expected impact. No output schema needed for a feedback tool.

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

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

Schema has 100% coverage with descriptions, but description adds value by explaining enum categories, optional context purpose, and message length limit (2000 chars). Slight additional clarity.

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 sends feedback to the Pipeworx team about bugs, missing features, or praise. It specifies the action (tell), resource (team), and purpose, distinguishing it from sibling tools which are unrelated.

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

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

Explicitly provides when to use: bugs, features, data gaps, praise. States what not to do (don't paste end-user prompts) and how to describe issues. No alternative tools exist for feedback, so guidance is comprehensive.

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 valuable context: no PII, aggregated counts only, caching behavior (5min-1h based on window), and data source (CF analytics-engine). 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?

Four sentences, front-loaded with core result, each sentence adds value (purpose, use cases, data privacy, caching). 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?

For a simple read-only tool with one optional parameter, the description covers purpose, usage, data origin, privacy, and caching. No output schema needed; annotations handle safety/freshness.

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

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

Only parameter 'window' has full schema coverage with enum. Description adds meaning by explaining trade-offs: shorter windows surface what's hot right now, longer windows show steady-state demand.

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

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

Clearly states it returns top tools, top packs, and total call volume over a recent window. Distinguishes from sibling tools like 'ask_pipeworx' or 'discover_tools' by specifying aggregated trending data.

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

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

Lists three specific use cases (discovering hot data sources, confirming popular tool, seeing alignment) and explains how window size affects results. Lacks explicit when-not-to-use but provides sufficient context for appropriate invocation.

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 show read-only, open-world, idempotent, non-destructive. Description goes beyond: details internal checks (monotonicity, partition sum, Jaccard similarity, placeholder filtering), fill check against live CLOB depth, and conditions when not to trade (realizable_edge_pp <=0). 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 relatively long. However, it is well-structured with clear section labels (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK) and front-loaded with the essential requirement. A minor reduction in detail could improve conciseness without losing value.

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

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

Given complexity (two modes, multiple checks, edge cases), description covers all aspects: required parameters, mode selection, internal logic, response structure, and ties to sibling tool. Even without output schema, it explains response fields and conditions, making it complete for an agent to understand and invoke correctly.

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

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

Schema coverage is 100% with descriptions for both parameters. Description adds significant meaning: explains event accepts slug or URL, topic as seed question, and provides real-world examples. Also clarifies behavior per parameter (single-event vs cross-event mode) beyond schema.

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

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

The description clearly states it finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes between single-event (event) and cross-event (topic) modes, each with specific use cases and examples, and differentiates from sibling tools like polymarket_edges and polymarket_fill_risk.

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

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

Explicitly states 'REQUIRES one of event or topic' with failure condition. Provides guidance on when to use each mode (event recommended for specific market, topic for cross-event scanning) and explains advantages of cross-event mode. References sibling tool polymarket_fill_risk for custom sizing, giving clear context for 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 readOnly, openWorld, idempotent, non-destructive. The description adds beyond annotations: explains caching ('Cached 1h at the KV level'), response segmentation, and diagnostic fields. No contradiction with annotations.

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

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

The description is detailed but well-structured with clear sections (model families, knobs, response top-level). While lengthy, the information is organized and relevant. Could trim some specific parameter values (e.g., α values) but overall effective.

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

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

For a complex tool with 9 parameters and no output schema, the description comprehensively explains output structure (by_segment segments, diagnostics), caching behavior, and exclusions (Fed bets). Provides sufficient context for correct invocation.

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

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

Schema coverage is 100% with descriptions. The description adds nuanced usage advice (e.g., adjusting slippage for thin partitions, purpose of min_liquidity as tradeable-edge filter). This enhances understanding beyond schema alone.

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

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

The description clearly states the tool's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It positions itself as a daily discovery tool ('what should I bet on today') and distinguishes from siblings like polymarket_arbitrage by focusing on Pipeworx data discrepancies.

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

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

The description implies usage for daily opportunity discovery but does not explicitly contrast with sibling tools or specify when not to use it. While it mentions tradeable-edge knobs, it lacks clear exclusion criteria or alternative tool recommendations.

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

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

Adds rich behavioral context beyond annotations: details on snapshot generation (cache-miss gaps), response structure (tracked, expired, snapshot_dates), and computation details (trend, decay, lifespan). Discloses bounded history and non-intraday decay.

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

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

Description is moderately long but efficiently packed: purpose first, then args, then detailed response structure. Every sentence adds value, though slight redundancy in listing defaults could be trimmed.

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 read-only tool with 2 optional params and no output schema, the description fully explains the response structure, meaning of fields (trend, decay_pp_per_day, lifespan), and limitations (TTL, snapshot gaps, intraday vs daily). No gaps.

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

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

Schema coverage is 100% (both params described). Description adds extra value by linking parameters to response fields (days controls lookback, window selects snapshot family) and explaining defaults and clamping. Provides more context than 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?

Description clearly states it provides edge persistence and decay telemetry from daily snapshots. It answers a specific question about how long an edge has existed and whether it's shrinking, and differentiates from sibling polymarket_edges by focusing on historical context.

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 guides use for historical edge analysis, distinguishes between fresh and aged edges, and notes limitations (60-day TTL, decay from daily closes not intraday). It doesn't explicitly exclude alternatives or compare to other siblings 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?

Description details what the tool computes: walks ladder, returns top_of_book, VWAP, slippage, verdicts, per-leg details, forced directional risk. Adds context beyond annotations (readOnly, idempotent, openWorld) 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?

Well-organized with clear sections (REQUIRES, SINGLE-MARKET, BASKET, usage note). Slightly lengthy but each sentence adds value; minor room for tightening.

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 covers all return fields for both modes, edge cases (thin_legs, forced_directional_risk), and rationale. Fully sufficient for agent to understand 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?

With 100% schema coverage, description adds rich meaning: clarifies size_usd interpretation per mode, side defaults, basket return fields. Goes well beyond schema descriptions.

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

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

Clearly states it checks realizable-vs-theoretical edge against live CLOB depth. Distinguishes two modes (single-market and basket), making it distinct from siblings like polymarket_arbitrage or polymarket_edges.

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

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

Explicitly advises use before acting on arb signals from polymarket_arbitrage or for trades above ~$500 on polymarket_edges. Explains why (thin books, partial basket fills cause directional risk).

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

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

Annotations already mark readOnlyHint, openWorldHint, idempotentHint, destructiveHint false. Description adds critical behavioral context: compatibility_warning conditions, temporal alignment, skipped cross-type/subtype counters. 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?

Well-structured with clear sections (modes, response, safety fields). Front-loaded with purpose. However, slightly verbose in safety field explanation; could be more concise without losing value.

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

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

Despite no output schema, the description fully explains the response structure, safety fields, and matching logic. Covers temporal alignment and skipped comparisons. For a complex tool, it provides complete context for correct invocation.

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

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

Schema coverage is 100%, but description significantly enriches each parameter: topic lists all 10 shortcuts, other parameters provide examples and explain override behavior. This adds meaning beyond the schema alone.

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

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

Description clearly states it computes cross-venue spread between Kalshi and Polymarket for the same resolving question. It distinguishes from siblings like polymarket_arbitrage by specifying cross-venue nature and two modes (topic shortcuts vs explicit pairing). The description is specific and informative.

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

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

Explicitly describes when to use (to find arbitrage opportunities across venues) and when not (if compatibility_warning fires, indicating non-equivalent bet shapes or unrelated events). It warns that most pre-mapped topics are not tradeable, preventing misuse. Modes are clearly distinguished.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds scope (anonymous IP, BYO key hash, account ID) and pairing info, which is useful but not essential given annotations.

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

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

Three sentences, front-loaded with purpose, no fluff. 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?

No output schema, but description implies return values (saved value or list of keys). Complete for a retrieval tool with one optional parameter.

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

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

Schema coverage is 100% and description adds context: key is for retrieval, omitting lists all keys. Provides examples of use cases. Adds meaning beyond schema.

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

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

Explicitly states it retrieves a value saved via remember or lists all keys. Uses specific verb 'retrieve' and resource 'saved value'. Distinct from sibling tools remember and forget.

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

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

Clearly says when to use (look up context stored earlier) and how (omit key to list). Mentions scope and pairing with remember/forget. Lacks explicit exclusions but context is clear.

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

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

The description states that setting mark_read:true flags returned events as read, modifying state for subsequent calls. This directly contradicts the readOnlyHint=true annotation, which implies no write operations. The annotation claims the tool is read-only, but the description describes a write side effect, making this a clear annotation 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 four sentences, each adding meaningful information without redundancy. It begins with the core purpose, then details returned fields, explains filtering and mark_read, and concludes with polling behavior and alternative access. Every sentence earns its place.

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

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

Given the tool has multiple parameters, no output schema, and annotations present, the description adequately covers key aspects: return fields, filtering, mark_read, polling suitability, and alternative access. It does not discuss pagination or response format, but the limit parameter and context overall are sufficient for an AI agent to use the tool effectively.

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

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

The input schema has 100% parameter description coverage, but the tool description adds contextual value by explaining the mark_read behavior ('flag returned events read so the next call only shows newer ones') and providing an example filter value ('sec_8k') for the type parameter. This goes beyond the schema's base descriptions.

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

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

The description starts with 'Pull fired events from your subscription feed', clearly stating the tool retrieves recent alerts. It details what each alert carries (source, citation_uri, raw payload) and distinguishes itself from sibling tools by focusing on alert retrieval with filtering and read-state management.

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

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

The description specifies when to use this tool: to pull fired events, filter by type and/or timestamp, and optionally mark events as read. It mentions polling works and notes an alternative access method (GET endpoint). However, it lacks explicit guidance on when not to use it or comparisons with specific siblings.

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

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

Beyond annotations (readOnlyHint, idempotentHint, etc.), the description discloses the tool fans out to multiple data sources (SEC, GDELT/GNews, USPTO), explains the fallback logic, notes a soft-fail for USPTO, and describes the return structure. No contradictions with annotations.

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

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

The description is front-loaded with example queries, uses clear and efficient language, and every sentence adds necessary context without redundancy. It is well-structured for its complexity.

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

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

Given the high schema coverage, lack of output schema, and tool complexity, the description adequately covers return structure (grouped changes, total count, URIs), data sources, and alternatives. No gaps identified.

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 significant value: it explains the 'since' parameter syntax (ISO date or relative shorthand like '7d'), suggests a default ('30d' or '1m'), and clarifies that 'type' only supports 'company', going beyond the schema's basics.

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 as a change feed for a company over a time window, with concrete example queries. It distinguishes itself from the sibling tool 'entity_profile' by specifying when to use each.

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 via example natural language queries, describes the fallback mechanism between GDELT and GNews, and instructs to use 'entity_profile' for static profile needs, covering both usage and alternatives.

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

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

Description adds context beyond annotations: scoping by identifier, persistence differences (authenticated vs anonymous, 24-hour retention). Annotations already indicate idempotentHint=true and non-destructive.

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

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

Four sentences, front-loaded with purpose, no wasted words. Could be slightly tighter but effective.

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

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

For a simple 2-parameter tool with no output schema, the description sufficiently covers usage, lifetime, and pairing with siblings.

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

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

Schema coverage is 100% with clear descriptions for 'key' and 'value'. The description mentions key-value pair but adds little beyond the schema's examples.

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

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

The description specifies the verb 'save', the resource 'data', and the context 'across this conversation or across sessions'. It distinguishes from sibling tools (recall, forget) by mentioning them as paired operations.

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 ('when you discover something worth carrying forward') and identifies alternatives ('Pair with recall to retrieve later, forget to delete').

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, covering safety. The description adds that each call cascades through multiple endpoints internally, which provides some behavioral context but does not contradict or significantly extend annotation-provided information.

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

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

The description is well-structured with examples, an explicit usage directive, and clear bullet-like formatting for types. It is slightly verbose with the internal cascading detail, but remains focused and front-loaded.

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

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

Despite lacking an output schema, the description fully covers the two entity types, input formats, output fields, and even citation URIs. It leaves no ambiguity about what the tool returns, making it contextually complete for an agent.

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

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

With 100% schema coverage, baseline is 3, but the description greatly enriches both parameters by explaining input variants (e.g., company: ticker, CIK, or name) and detailing outputs for each type, including citation URIs. This goes well beyond the schema's brief property 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 resolves a name to a canonical/official identifier, using specific examples like ticker or CIK for companies and RxCUI for drugs. It also distinguishes its role as the first step for ID lookup among siblings that likely require IDs.

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

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

Explicitly tells the agent to 'Use FIRST whenever you have a name but need an ID,' providing clear guidance on when to invoke the tool. Also mentions it replaces 2-3 manual lookups, reinforcing its utility.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds that it internally calls ai_visibility_check for each entity and returns a ranked list with score, confidence, signal density. No contradictions; adds useful detail 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 three sentences, front-loaded with the main action, then details. No wasted words. Perfectly concise for the information conveyed.

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

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

Given the tool's complexity (4 parameters, comparative function), the description covers the core behavior, return fields, and use case. No output schema but the return values are summarized. Adequately complete without being overly verbose.

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

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

Schema covers 100% of parameters with detailed descriptions. The main description adds the nuance that the first entity is treated as the 'subject' and the rest as competitors. This provides value beyond the schema's base 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 it compares AI visibility across multiple entities side-by-side, using ai_visibility_check, and produces a ranked list. This distinguishes it from sibling tools like ai_visibility_check (single entity) and compare_entities (generic comparison).

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

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

The description mentions it is useful for competitive AI-marketing audits and implies it is for multi-entity comparison. The reference to probing each entity with ai_visibility_check provides context, but no explicit exclusion for single-entity use (covered by sibling tool). Clear enough.

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

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

The description adds behavioral context beyond annotations, such as partial failure handling (bundlephobia first measurement can take 5-30s, sources_failed lists timeouts) and the return format (summary block with specific fields). This aligns with annotations (readOnlyHint, idempotentHint) and adds valuable detail.

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 information-dense and front-loaded with composite nature and use case. Every sentence adds value, though it is relatively long. Could be slightly trimmed but overall efficient for the complexity.

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

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

Given no output schema, the description thoroughly lists return values (summary fields, per-advisory detail, links, alternative versions) and covers edge cases (partial failures, ecosystem scope, measurement delays). It provides sufficient context for an agent to understand inputs, 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 description coverage is 100%, so baseline is 3. The description provides extra context for package param (accepts scoped packages with example) but does not significantly enhance understanding beyond schema. No additional semantic depth for version.

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

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

The description clearly states the tool's purpose: a composite check for adding npm packages, covering safety, popularity, and size. It specifies the verb 'scan' and resource 'npm package dependency', and distinguishes from sibling tools by focusing on a specific ecosystem and combining multiple data sources.

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

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

Explicitly tells when to use: when an agent asks about safety, popularity, size, or cost of adding a package. It also notes that the tool is npm-only in v1 and suggests alternatives for other ecosystems (deps.dev directly), providing clear guidance on when not to use.

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

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

Annotations already indicate readOnly, openWorld, idempotent, non-destructive. The description adds specifics: character offsets, similarity scores, 200K char cap with truncation flag, embedding model details, which provide useful behavioral context beyond annotations.

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

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

The description is a single, well-structured paragraph that front-loads the purpose and key details. Every sentence adds value, with no redundancy.

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

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

Despite no output schema, the description mentions return values (passages with offsets and similarity scores) and covers important behaviors like truncation and pairing with another tool. It is complete for the tool's complexity.

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

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

Schema coverage is 100% with adequate descriptions for each parameter. The tool description adds implementation details (BGE-base-en, cosine, overlapping windows) but does not significantly enhance parameter meaning beyond the schema.

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

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

The description clearly states 'Semantic search INSIDE a fetched record,' specifying the action and resource. It distinguishes itself from siblings by mentioning pairing with ask_pipeworx_grounded.

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

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

The description explicitly says 'Use when the record is too big to cram into the prompt' and provides a clear example (SEC 10-K). It does not explicitly state when-not to use, 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?

Discloses key behaviors beyond annotations: OAuth requirement, persistence, delivery channel details (email, SMS with cap, webhook with signature and auto-disable). Annotations already indicate idempotence and non-destructiveness, but description adds rich context.

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

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

Front-loaded with core function and return value. Well-structured with separate mentions for types and delivery. Slightly verbose (e.g., repeating phone verification) but overall efficient.

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

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

Covers all essential context: return value, requirements, type-specific params, delivery options, rate limits, and failure handling (webhook auto-disable). No output schema, but description compensates.

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

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

Adds significant value beyond schema: examples for each subscription type, required fields, delivery constraints (phone verification, SMS cap, webhook signing). Schema descriptions already present, but description provides actionable details.

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

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

Description clearly states action ('Create...subscription'), resource ('subscription'), and return value ('new subscription id'). Distinguishes from siblings like list_subscriptions and unsubscribe.

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

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

Explicitly states prerequisites (Pipeworx OAuth account, not anonymous/BYO). Lists supported types and delivery channels. Could be more explicit about when not to use, but sibling context helps.

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 show readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds that it returns 'category-bucketed example questions...with exact tool + argument shape', which is valuable behavioral context beyond annotations. No contradictions.

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

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

The description is front-loaded with common queries and structured into two logical parts: first the trigger phrases and overall purpose, then details of output and usage. Slightly verbose but earns its length with dense useful 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 readOnly tool with no output schema, the description sufficiently covers what it returns, when to use it, and how to invoke it. The addition of real-world examples and the mention of 'live catalog' adds context that substitutes for an output schema.

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

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

Schema coverage is 100% with a single optional parameter. The description adds concrete examples of valid topic values and explains the behavior when omitted ('full spread'), enriching the schema's brief description.

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

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

The description explicitly states the tool's purpose: onboarding entry point for learning what Pipeworx can do. It lists multiple trigger phrases and clearly distinguishes from siblings by saying it returns example questions with tool calls, not actual answers.

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 concrete guidance: 'Use this FIRST when you do not yet know what Pipeworx can do for you', explains when to omit topic vs. pass a specific focus, and mentions it teaches how to call meta-tools. This clearly differentiates from alternatives like ask_pipeworx.

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

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

The description adds context beyond annotations: ownership enforcement and deactivation (not deletion) behavior. Annotations already indicate non-destructive and idempotent, and the description complements them 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 succinct with two sentences: first states the action, second adds usage constraints and side effects. No unnecessary words.

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

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

For a simple tool with one parameter and no output schema, the description covers purpose, ownership rules, and behavioral consequences, fully addressing complexity.

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

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

The parameter id is fully described in the schema ('Subscription id (uuid) returned by subscribe') with 100% coverage. The description adds no new parameter information, so baseline score of 3 is appropriate.

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

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

The description clearly states the action (Cancel a subscription by id) and resource (subscription), distinguishing it from sibling tools like subscribe (adds subscription) and list_subscriptions (lists all).

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 mentions ownership enforcement (only cancel own subscriptions), which sets clear prerequisites. Also explains the deactivation vs deletion behavior and directs users to recent_alerts for historical events.

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

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

Annotations already cover read-only, idempotent, open-world, and non-destructive traits. The description adds valuable behavioral details: returns a verdict (with possible values), structured data, citation, and percent delta, and replaces multiple sequential calls. 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 well-structured, starting with example triggers, then intended usage, then scope, then return details. It is slightly verbose but every sentence adds value. No wasted words, but could be tightened slightly.

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

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

Despite lacking an output schema, the description thoroughly explains the return structure (verdict types, extracted form, actual value, citation, delta). Combined with annotations, the agent has complete information to invoke and interpret 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?

The schema describes the single parameter 'claim' adequately, and the description further clarifies the natural-language format and the supported claim types (company-financial). With 100% schema coverage, the description adds useful context 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 as natural-language claim verification against authoritative sources, with specific examples of user intents and scope (company-financial claims via SEC EDGAR + XBRL). It distinctly differentiates from sibling tools by being a direct verification tool that replaces multiple sequential calls.

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

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

The description provides clear guidance on when to use the tool ('whenever needs to check factual correctness'), and implicitly notes limitations (v1 supports only company-financial claims). It does not explicitly state when not to use or list alternatives, but the context is sufficient for correct selection.

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